Firebase vs Convex

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Convex
   Firebase—none0/10

   A direct probe shows firebase.google.com/llms.txt returns 404, and no evidence pack item shows any agent-oriented docs bundle or llms.txt equivalent; the MCP server (firebase-docs-12) is a separate tool-integration axis, not an agent-readable docs file.

   • [probe] “PROBE llms.txt: HTTP 404 at https://firebase.google.com/llms.txt”

   proof ↗⚑ flag

   Convex✓fullprobed8/10

   Convex confirmed hosts a live llms.txt (HTTP 200) plus a dedicated agent-setup.md file explicitly aimed at making 'your agent a Convex expert,' directly satisfying the story. missing for 10: no independent/third-party confirmation of agents actually consuming these files successfully, and per-page .md docs return 404 so coverage is limited to the root llms.txt/agent-setup files rather than full doc-tree markdown mirrors.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.convex.dev/llms.txt # Convex Documentation > For general information about Convex, read [https://w…”
   • [claimed-docs] “Make your agent a Convex expert: Get Convex-ready by following https://www.convex.dev/agent-setup.md”
   • [probe] “PROBE docs-md: HTTP 404 at https://docs.convex.dev/home.md”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Firebase~partialprobed6/10

   Firebase ships a scriptable CLI (firebase-tools) that can deploy code, manage hosting, import/export auth data, and run a Local Emulator Suite for offline integration testing/QA and mocha-based unit tests — all of which are usable in a headless/CI context (firebase-docs-8, firebase-docs-9, firebase-docs-24, firebase-docs-31, firebase-gh-1/2/3). However, there is no explicit CI/CD pipeline documentation (e.g., GitHub Actions integration, service-account auth for non-interactive CLI use) or independent confirmation of CI usage. Missing for 10: explicit CI/CD integration docs (e.g., GitHub Actions workflow), non-interactive auth guidance for automated environments, and independent/hands-on evidence of running the emulator suite or CLI in a CI pipeline.

   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “This means you can connect your app directly to these emulators to perform integration testing or QA without touching production data.”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [claimed-docs] “Unit Tests: using the Firebase Test SDK, you can write unit tests in Node.js using the mocha test runner.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site”
   • [github] “Import/Export users into/from Firebase Auth”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”

   proof ↗⚑ flag

   Convex~partialprobed6/10

   Convex ships a documented CLI (`npx convex run`, `npx convex import`, `npx convex deploy` implied, `npx convex logs`) and HTTP API for calling functions, both of which are automatable/scriptable in CI, plus self-hosting options for full non-interactive control. However, there is no explicit documentation of a headless/non-interactive CI mode, no CI recipe or GitHub Actions example, and the dev CLI is described as a filesystem-watching interactive workflow rather than an explicit CI-first mode. missing for 10: explicit CI/automation docs or examples (e.g., GitHub Actions integration, non-interactive deploy flags), confirmation that `npx convex deploy` runs fully headlessly without auth prompts.

   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “`npx convex import` — Import data from a file to your deployment”
   • [claimed-docs] “`npx convex logs` — Watch logs from your deployment”
   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”
   • [probe] “official CLI documented at https://docs.convex.dev/cli/overview”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   Firebase—none0/10

   Evidence only shows Firebase publishing its own MCP server for external AI tools (Claude, Cursor, VS Code Copilot, etc.) to consume — the opposite direction from this story, which asks whether Firebase itself (e.g., via Gemini in Firebase) can act as an MCP client and consume external MCP servers' tools. No evidence indicates Firebase's Gemini assistant or console supports plugging in external MCP servers. Missing for 10: any documentation of Firebase acting as an MCP client, any way to register external MCP servers within Firebase's own AI features.

   • [claimed-docs] “The Firebase MCP server works with any tool that can act as an MCP client, including: Antigravity, Claude Code and Claude Desktop, Cline, Cu…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”

   proof ↗⚑ flag

   Convex—none0/10

   All MCP-related evidence describes Convex shipping its OWN MCP server so external AI agents can call Convex's tools (convex-docs-10, convex-probe-4, convex-docs-28) — this is the opposite direction from the story, which asks whether Convex itself can plug in and consume external MCP servers' tools. No evidence shows Convex acting as an MCP client or invoking third-party MCP tool servers from its backend/actions.

   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Firebase
   Firebase✓fullprobed9/10

   Firebase ships an official documented MCP server that works with any MCP client tool (Antigravity, Claude Code/Desktop, Cline, Cursor, VS Code Copilot, Windsurf, etc.), enabling agents to manage Firebase projects, Auth, Firestore, and more. This is corroborated by both docs and a dedicated probe confirming the official page. Missing for 10: independent hands-on community report validating the MCP server's real-world reliability.

   • [claimed-docs] “The Firebase MCP server works with any tool that can act as an MCP client, including: Antigravity, Claude Code and Claude Desktop, Cline, Cu…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”

   proof ↗⚑ flag

   Convex✓fullprobed8/10

   Convex ships an official documented MCP server (docs.convex.dev/ai/convex-mcp-server) that exposes tools for AI agents to interact with a Convex deployment, with a safety note that it restricts production access by default, and this is corroborated by a direct probe confirming the doc page exists. Convex is a backend/database product (not itself an agent), so serving an MCP server is squarely within its category. Missing for 10: independent/hands-on community confirmation of the MCP server working in practice, and more detail on the specific tool set exposed.

   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Firebase✓fullprobed8/10

   Firebase ships an official CLI (firebase-tools) documented both in GitHub and Firebase docs, covering deploy, hosting, auth, and Firestore data management, and is corroborated by a dedicated CLI docs page (firebase-probe-4). This CLI is the standard tool for automating Firebase workflows, which AI-native/agentic users would drive programmatically or via the complementary MCP server for AI agents. missing for 10: explicit documentation of AI-native features built into the CLI itself (e.g., natural-language command generation) beyond its use as an MCP-server backend.

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site”
   • [github] “Import/Export users into/from Firebase Auth”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”
   • [claimed-docs] “The Firebase MCP server works with any tool that can act as an MCP client, including: Antigravity, Claude Code and Claude Desktop, Cline, Cu…”

   proof ↗⚑ flag

   Convex✓fullprobed8/10

   Convex ships an official CLI (npx convex ...) with documented commands for dev workflow, running functions, importing data, logs, and insights, and it explicitly integrates with AI-native workflows via agent setup docs and MCP tooling. missing for 10: independent/hands-on third-party corroboration of the CLI's AI-native ergonomics beyond first-party docs, and no explicit versioning/stability notes for CLI commands.

   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “`npx convex import` — Import data from a file to your deployment”
   • [claimed-docs] “`npx convex insights` — Show health insights for your deployment”
   • [claimed-docs] “`npx convex logs` — Watch logs from your deployment”
   • [claimed-docs] “Make your agent a Convex expert: Get Convex-ready by following https://www.convex.dev/agent-setup.md”
   • [probe] “official CLI documented at https://docs.convex.dev/cli/overview”

   proof ↗⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round drawn
   Firebase✓fullprobed8/10

   Firebase exposes a well-documented public surface for programmatic/agentic use: the official CLI (firebase-tools) for deploying, managing data, and auth; Admin/REST SDKs for Firestore, Auth, and Functions; and a dedicated first-party MCP server that lets AI agents (Claude, Cursor, VS Code Copilot, etc.) manage Firebase projects, auth, and Firestore data directly. missing for 10: a discoverable machine-readable spec (openapi.json/llms.txt both 404), and independent hands-on confirmation of the MCP server working reliably in production agent workflows

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [claimed-docs] “The Firebase MCP server works with any tool that can act as an MCP client, including: Antigravity, Claude Code and Claude Desktop, Cline, Cu…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”

   proof ↗⚑ flag

   Convex✓fullprobed8/10

   Convex documents a public HTTP API that exposes deployment functions as callable endpoints, a full-featured CLI for scripting deployments, and an official MCP server specifically for AI agents to interact with the deployment — together giving an AI-native user multiple documented, programmatic ways to drive the product. Missing for 10: a formal OpenAPI/swagger spec (probes found only 404s) and independent hands-on corroboration of third-party API usage.

   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [probe] “official CLI documented at https://docs.convex.dev/cli/overview”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.convex.dev/openapi.json, https://docs.convex.dev/swagger.json, https://docs.convex.dev/…”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Convex
   Firebase—none0/10

   Firebase has Security Rules and Identity Platform for general access control, but no evidence describes issuing scoped or least-privilege API credentials specifically for an AI agent (e.g., a restricted service-account/API-key flow tied to MCP or agent use). The MCP server docs only describe what an agent-connected editor can do, not how to scope its permissions. missing for 10: documentation of agent-specific scoped credentials/service accounts, least-privilege API key issuance workflow, any first-party or community confirmation of this capability.

   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [claimed-docs] “Firebase Security Rules leverage extensible, flexible configuration languages to define what data your users can access for Realtime Databas…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”

   proof ↗⚑ flag

   Convex~partialclaimed3/10

   The only relevant evidence is that Convex's MCP server is restricted from production deployments by default as a safety measure, which is a coarse, binary dev/prod restriction rather than true scoped/least-privilege credential issuance for agents (e.g., granular API keys, role-based tokens, or fine-grained permission scopes). Missing for 10: documented ability to mint scoped API keys/tokens per agent, granular permission models, or per-function/table credential scoping.

   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Firebase✓fullprobed8/10

   Firebase provides official SDKs across Firestore, Auth, Functions, Storage, and Rules, well documented with first-party docs and CLI (firebase-tools), plus emulator suite for local dev and testing. Community evidence corroborates real-world usage of these SDKs for building apps. missing for 10: independent hands-on validation specifically of SDK quality/versioning for AI-native workflows, and no explicit llms.txt/openapi spec found (probe results show 404s) which would strengthen AI-native discoverability.

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “FirebaseUI provides a drop-in auth solution that handles the UI flows for signing in users with email addresses and passwords, phone numbers…”
   • [claimed-docs] “The Firebase Authentication SDK provides methods that allow users to sign in with their Google, Facebook, Twitter, and GitHub accounts.”
   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”
   • [community] “I'm a big fan of firebase and use it whenever I can. The reason it's appealing is the suite of tools and how well they work together for boo…”

   proof ↗⚑ flag

   Convex✓fullprobed8/10

   Convex ships official SDKs/framework integrations for React, Next.js, Remix, TanStack Start, React Native, Vue, Nuxt, and Svelte, backed by typed client libraries, CLI tooling, and generated types, plus explicit AI-native tooling (MCP server, agent-setup guide) that lets AI-native developers build against these SDKs directly. Missing for 10: independent/hands-on third-party verification of SDK quality/completeness beyond vendor docs, and no OpenAPI/REST spec for non-JS ecosystems.

   • [claimed-docs] “Using your favorite frameworks: * React * Next.js * Remix * TanStack Start * React Native * Vue * Nuxt * Svelte”
   • [claimed-docs] “Start a new Convex project![...]`npm create convex@latest`”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “Make your agent a Convex expert: Get Convex-ready by following https://www.convex.dev/agent-setup.md”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”
   • [probe] “official CLI documented at https://docs.convex.dev/cli/overview”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Firebase—none0/10

   Firebase evidence shows event-driven Cloud Functions triggers and real-time listeners (Firestore/RTDB), but no documented webhook subscription mechanism for external endpoints to receive events; no first-party or community evidence of a webhooks feature.

   ⚑ flag

   Convex—none0/10

   Convex exposes HTTP endpoints so external clients can call Convex functions (docs-9, docs-31), but there is no evidence of an outbound webhook mechanism where Convex notifies subscribers of database/event changes. This is a fair capability for a reactive backend to offer, but no such feature is documented.

   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Firebase
   Firebase~partialclaimed6/10

   Firebase documents Gemini in Firebase providing AI-generated insights and suggestions from app data — e.g., actionable crash root-cause analysis and fix suggestions (Crashlytics) and summarization/recommendations for messaging campaign performance — directly matching the story's intent. However, this is scoped to specific data types (crash reports, messaging analytics) rather than general insights across all stored data (e.g., Firestore documents), and no independent/hands-on evidence corroborates the quality of these AI suggestions. Missing for 10: broader data-insight coverage (e.g., Firestore/database content analysis), independent user validation of insight quality.

   • [claimed-docs] “AI assistance provides actionable insights into your app's crashes, including a full description of the issue, information about possible ro…”
   • [claimed-docs] “Gemini in Firebase can summarize and analyze your messaging campaigns, providing actionable recommendations to improve performance.”
   • [claimed-docs] “If you use Crashlytics and enable Gemini in Firebase, you can get AI assistance for debugging and troubleshooting issues in your Apple and A…”
   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”

   proof ↗⚑ flag

   Convex—none0/10

   Convex provides infrastructure (vector search, MCP server) that lets developers build AI features on top of their data, and a CLI 'insights' command that surfaces deployment health metrics — but there is no evidence Convex itself surfaces AI-generated insights or suggestions about the user's actual application data inside the product.

   • [claimed-docs] “`npx convex insights` — Show health insights for your deployment”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector... enable you to provide useful context to LLMs for AI powere…”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Firebase
   Firebase✓fullclaimed8/10

   Firebase Cloud Functions explicitly support autonomous, event-driven background execution, including triggers from Firebase/Cloud events, HTTPS requests, and Cloud Scheduler jobs, letting users run scheduled or event-triggered automations without manual intervention. Docs also show one-command deployment and auto-scaling for these functions. Missing for 10: independent/hands-on corroboration of scheduler reliability and any dispute resolution for the older community complaint about lacking scheduled tasks (which predates Cloud Scheduler support).

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “The functions you write can respond to events generated by various Firebase and Google Cloud features, from Firebase Authentication triggers…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence pack has no mention of Convex scheduled functions, cron jobs, or any mechanism for autonomous background automation; it only covers reactive queries, HTTP endpoints, and an MCP server for interactive agent access to a deployment. Missing for 10: any citation of cron/scheduled functions, background job triggers, or autonomous workflow execution.

   ⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Firebase
   Firebase✓fullclaimed8/10

   Firebase ships Gemini in Firebase, a built-in natural-language AI assistant embedded in the console that answers product questions, generates code, and provides crash/debugging insights and messaging analytics — directly fulfilling task delegation to a built-in AI assistant. missing for 10: independent/hands-on verification of Gemini in Firebase's task-execution quality beyond first-party docs, and clearer detail on the scope of tasks it can autonomously complete versus just advise on.

   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”
   • [claimed-docs] “AI assistance provides actionable insights into your app's crashes, including a full description of the issue, information about possible ro…”
   • [claimed-docs] “Gemini in Firebase can summarize and analyze your messaging campaigns, providing actionable recommendations to improve performance.”
   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”
   • [claimed-docs] “If you use Crashlytics and enable Gemini in Firebase, you can get AI assistance for debugging and troubleshooting issues in your Apple and A…”

   proof ↗⚑ flag

   Convex—none0/10

   Convex ships an MCP server and CLI that let external AI agents interact with a Convex deployment, and docs mention it 'works great with coding agents,' but this is agent-to-Convex tooling, not a built-in assistant embedded inside Convex itself that a user can delegate tasks to. No evidence of an in-product chat/assistant feature exists in the pack.

   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “Convex works great with coding agents. Starting a new project is as easy as asking your agent to create a new app with Convex.”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Firebase
   Firebase✓fullprobed8/10

   Firebase documents both a natural-language chat interface (Gemini in Firebase) for getting answers, generating code, and troubleshooting, and an official MCP server that lets AI editors/agents create and manage Firebase projects, Auth users, and Firestore data via natural-language commands routed through MCP clients like Claude Code, Cursor, VS Code Copilot, etc. Missing for 10: independent/hands-on validation that MCP-driven natural-language operations reliably perform complex actions, and confirmation Gemini in Firebase supports action-taking beyond Q&A/insights.

   • [claimed-docs] “The Firebase MCP server works with any tool that can act as an MCP client, including: Antigravity, Claude Code and Claude Desktop, Cline, Cu…”
   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”

   proof ↗⚑ flag

   Convex~partialprobed6/10

   Convex offers an official MCP server so AI agents can inspect/query deployments in natural language, plus agent-setup guidance and messaging that it 'works great with coding agents' for scaffolding projects via natural-language requests. However, this relies entirely on external coding agents/MCP clients rather than a built-in NL interface, and production access is restricted by default. Missing for 10: a first-party conversational/NL interface within Convex itself, and independent hands-on evidence of natural-language operation succeeding end-to-end.

   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “Make your agent a Convex expert: Get Convex-ready by following https://www.convex.dev/agent-setup.md”
   • [claimed-docs] “Convex works great with coding agents. Starting a new project is as easy as asking your agent to create a new app with Convex.”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Firebase—none0/10

   No evidence of an interactive API reference with runnable examples; probes confirm llms.txt and openapi endpoints return 404, and docs pack contains no mention of a live/interactive reference or embedded runnable code samples.

   • [probe] “PROBE llms.txt: HTTP 404 at https://firebase.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://firebase.google.com/openapi.json, https://firebase.google.com/swagger.json, https://firebase…”

   proof ↗⚑ flag

   Convex—none0/10

   No evidence of an interactive API reference or runnable-example playground; probes explicitly show no OpenAPI/Swagger spec (404s) and only static docs pages plus an llms.txt for AI consumption. Convex offers CLI, MCP server, and HTTP API docs, but nothing indicating a browsable, runnable API explorer.

   • [probe] “PROBE docs-md: HTTP 404 at https://docs.convex.dev/home.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.convex.dev/openapi.json, https://docs.convex.dev/swagger.json, https://docs.convex.dev/…”
   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Firebase—none0/10

   Probes for llms.txt and common OpenAPI/swagger spec paths all returned 404, and no documentation in the evidence pack references a downloadable OpenAPI/Swagger spec for Firebase APIs.

   • [probe] “PROBE llms.txt: HTTP 404 at https://firebase.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://firebase.google.com/openapi.json, https://firebase.google.com/swagger.json, https://firebase…”

   proof ↗⚑ flag

   Convex—none0/10

   A direct probe for OpenAPI/swagger spec files at all standard candidate paths returned 404, and no documentation mentions a downloadable API spec despite Convex exposing HTTP endpoints for functions.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.convex.dev/openapi.json, https://docs.convex.dev/swagger.json, https://docs.convex.dev/…”
   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Firebase✓fullclaimed8/10

   Firebase's Local Emulator Suite explicitly lets developers connect apps to emulators for integration testing or QA 'without touching production data,' covering Firestore, Auth, Functions, Storage, Hosting, and more, with unit test support via mocha. missing for 10: independent/hands-on corroboration of emulator fidelity and AI-native/agent-specific usage examples beyond generic dev testing.

   • [claimed-docs] “This means you can connect your app directly to these emulators to perform integration testing or QA without touching production data.”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [claimed-docs] “Unit Tests: using the Firebase Test SDK, you can write unit tests in Node.js using the mocha test runner.”

   proof ↗⚑ flag

   Convex✓fullclaimed8/10

   Convex has separate dev/production deployments (npx convex dev pushes to dev deployment, not prod) and the official MCP server explicitly blocks access to production deployments by default as a safety measure to prevent accidental modifications to production data, directly enabling sandboxed testing for AI agents. missing for 10: independent/hands-on corroboration of this safety boundary actually holding in practice, and no explicit mention of a dedicated 'staging' environment distinct from dev/prod.

   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Firebase—none0/10

   No evidence pack item documents API versioning schemes or a deprecation policy for Firebase's APIs/SDKs; probes for openapi.json/llms.txt both 404, and no docs reference version support windows or deprecation timelines.

   • [probe] “PROBE llms.txt: HTTP 404 at https://firebase.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://firebase.google.com/openapi.json, https://firebase.google.com/swagger.json, https://firebase…”

   proof ↗⚑ flag

   Convex—none0/10

   No evidence of API versioning scheme or a documented deprecation policy; OpenAPI spec probe returned 404s and no changelog/versioning docs are cited.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.convex.dev/openapi.json, https://docs.convex.dev/swagger.json, https://docs.convex.dev/…”

   proof ↗⚑ flag

Ai assist

1. ai-native userAsk an AI assistant in the dashboard to write queries, debug errors, and explain my backend

   weight 2 · round to Firebase
   Firebase✓fullclaimed8/10

   Firebase ships Gemini in Firebase, a natural-language chat interface in the dashboard that answers product questions, generates code, and provides AI-driven crash/debugging insights, directly matching the story of asking an AI assistant to write queries, debug, and explain the backend. missing for 10: independent hands-on user reports validating query-writing/debugging accuracy in Gemini in Firebase specifically (only vendor docs cited).

   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”
   • [claimed-docs] “AI assistance provides actionable insights into your app's crashes, including a full description of the issue, information about possible ro…”
   • [claimed-docs] “Get instant answers to questions about Firebase products and features, generate code for faster development, and shorten your troubleshootin…”
   • [claimed-docs] “If you use Crashlytics and enable Gemini in Firebase, you can get AI assistance for debugging and troubleshooting issues in your Apple and A…”

   proof ↗⚑ flag

   Convex—none0/10

   Evidence shows an official MCP server that lets external AI agents (e.g., coding assistants in an IDE) query/mutate/debug a Convex deployment, but nothing describes an AI assistant embedded within the Convex dashboard UI itself for writing queries, debugging errors, or explaining the backend. The story specifically asks about an in-dashboard assistant, which is not evidenced.

   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [claimed-docs] “Make your agent a Convex expert: Get Convex-ready by following https://www.convex.dev/agent-setup.md”

   proof ↗⚑ flag

Vector

1. developerStore embeddings and run vector similarity search for AI features

   weight 3 · round drawn
   Firebase✓fullclaimed8/10

   Firebase documents dedicated Cloud Firestore vector search functionality with KNN vector search, including storing vector values and creating/managing KNN vector indexes, directly matching the story. Missing for 10: independent/hands-on developer corroboration of vector search in production and details on scale/performance limits.

   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches”
   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches using the following techniques”
   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches using the following techniques: Store vec…”

   proof ↗⚑ flag

   Convex✓fullclaimed8/10

   Convex documents native vector search over stored documents specifically framed for embeddings and LLM context/recommendations use cases (convex-docs-7, convex-docs-14, convex-docs-29, convex-docs-35), integrated directly into its database without extra infrastructure. Missing for 10: independent hands-on benchmarks or community validation of vector search at scale, and details on index configuration/limits.

   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector... enable you to provide useful context to LLMs for AI powere…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector. Typically, vectors will be embeddings which are numerical re…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector... enable you to provide useful context to LLMs for AI powere…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector.”

   proof ↗⚑ flag

Authentication

1. developerAdd email/password and social OAuth sign-in with the platform SDK in minutes

   weight 3 · round to Firebase
   Firebase✓fullcommunity8/10

   Firebase Authentication SDK explicitly supports email/password plus Google, Facebook, Twitter, and GitHub OAuth sign-in, and FirebaseUI offers a drop-in solution handling these sign-in flows out of the box, matching the 'minutes' setup claim; community feedback also corroborates Firebase's ease of bootstrapping auth alongside other services. missing for 10: independent hands-on account of specifically timing/adding OAuth sign-in setup, and no mention of other providers like Apple/Microsoft.

   • [claimed-docs] “FirebaseUI provides a drop-in auth solution that handles the UI flows for signing in users with email addresses and passwords, phone numbers…”
   • [claimed-docs] “The Firebase Authentication SDK provides methods that allow users to sign in with their Google, Facebook, Twitter, and GitHub accounts.”
   • [claimed-docs] “FirebaseUI provides a drop-in auth solution that handles the UI flows for signing in users with email addresses and passwords, phone numbers…”
   • [community] “I'm a big fan of firebase and use it whenever I can. The reason it's appealing is the suite of tools and how well they work together for boo…”
   • [community] “One of the things I find quite nice about firebase is the powerful separation between data retrieval/update logic and the enforcement of acc…”

   proof ↗⚑ flag

   Convex~partialclaimed6/10

   Convex docs confirm Convex Auth library supports password, social OAuth, OTP email/SMS sign-in, plus recommended third-party providers like Clerk/Auth0/WorkOS with SDK integration guidance for React/Next.js/React Native, but the evidence doesn't show a single unified 'minutes' quick-start flow or hands-on confirmation of setup speed. missing for 10: a concrete quick-start walkthrough/tutorial demonstrating minutes-level setup, independent developer testimony confirming ease/speed, and explicit code snippets for combined email/password + OAuth configuration.

   • [claimed-docs] “Clerk has great Next.js and React Native support”
   • [claimed-docs] “you can implement auth directly in Convex with the Convex Auth library... helps you build a custom sign-up/sign-in flow via social identity …”
   • [claimed-docs] “Clerk has great Next.js and React Native support ... WorkOS AuthKit is built for B2B apps ... Auth0 is more established with more bells and …”
   • [claimed-docs] “For client-side React and React Native mobile apps you can implement auth directly in Convex with the Convex Auth library.”

   proof ↗⚑ flag

2. platform-engineerRequire MFA and enterprise SSO (SAML/OIDC) for my application users

   weight 2 · round to Firebase
   Firebase~partialclaimed6/10

   Firebase's own docs state that native Firebase Authentication does not include MFA or enterprise SSO by default — these require upgrading to 'Firebase Authentication with Identity Platform,' which unlocks multi-factor authentication, SAML and generic OpenID Connect support, and enterprise-level support (firebase-docs-28). This confirms the capability exists but only via a paid upgrade path, not as a standard included feature — a significant caveat for a platform engineer evaluating baseline auth. Missing for 10: first-party documentation detailing MFA/SSO configuration steps, enforcement policies, and independent/hands-on validation of enterprise SSO setup.

   • [claimed-docs] “When you upgrade to Firebase Authentication with Identity Platform, you unlock additional features, such as multi-factor authentication, blo…”

   proof ↗⚑ flag

   Convex—none0/10

   Convex docs describe auth via third-party providers (Clerk, WorkOS AuthKit, Auth0) or its own Convex Auth library for social/email/password sign-in, but there is no evidence of built-in enterprise SSO (SAML/OIDC) or MFA enforcement controls for a platform engineer to configure directly; these would depend entirely on the chosen third-party provider's capabilities, which aren't documented here.

   • [claimed-docs] “Clerk has great Next.js and React Native support”
   • [claimed-docs] “you can implement auth directly in Convex with the Convex Auth library... helps you build a custom sign-up/sign-in flow via social identity …”
   • [claimed-docs] “Clerk has great Next.js and React Native support ... WorkOS AuthKit is built for B2B apps ... Auth0 is more established with more bells and …”
   • [claimed-docs] “For client-side React and React Native mobile apps you can implement auth directly in Convex with the Convex Auth library.”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Firebase
   Firebase~partialcommunity5/10

   Firebase provides some bulk-oriented capabilities—bulk import/export of Auth users via the CLI (firebase-gh-1, firebase-gh-3), multi-filter/sort queries in Firestore (firebase-docs-2), and MongoDB-compatible API access that could support bulk driver operations (firebase-docs-4/16/27)—but there's no direct documentation of a native batch-write/bulk-update API for arbitrary large-scale item operations, and community feedback notes limitations like lacking count queries without full downloads (firebase-comm-16). missing for 10: explicit batch-write/bulk-update API documentation, evidence of scale/performance for bulk operations, and independent hands-on confirmation of bulk data manipulation beyond auth import/export.

   • [claimed-docs] “Your queries can include multiple, chained filters and combine filtering and sorting.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Import/Export users into/from Firebase Auth”
   • [claimed-docs] “Cloud Firestore offers a MongoDB-compatible API. You can use existing MongoDB application code, drivers, tools, and the open-source ecosyste…”
   • [community] “When will it support a count query? Now to be able to count number of children I have to download all the data. Count is such an important f…”

   proof ↗⚑ flag

   Convex~partialclaimed4/10

   Convex supports bulk data import via `npx convex import` and lets mutations/queries run arbitrary JS over many documents, and the MCP server lets AI agents call these functions on a deployment. However, there's no documented explicit bulk-write/update/delete API, batch size limits, or a concrete example of an AI agent performing a bulk operation end-to-end. missing for 10: explicit bulk mutation/update/delete API docs, batch operation guarantees/limits, hands-on evidence of an AI agent executing bulk operations via MCP or CLI.

   • [claimed-docs] “`npx convex import` — Import data from a file to your deployment”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Firebase
   Firebase✓fullclaimed8/10

   Firebase's Cloud Functions is explicitly a serverless event-trigger system: it runs backend code automatically in response to background events, HTTPS requests, Admin SDK, Auth triggers, Storage triggers, or Cloud Scheduler jobs, directly matching the 'rules that trigger actions on events' story. This is well documented across multiple first-party pages with concrete trigger types listed. Missing for 10: independent/hands-on corroboration of trigger reliability at scale, and clarification of any AI-native-specific tooling for defining these rules beyond standard docs.

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “The functions you write can respond to events generated by various Firebase and Google Cloud features, from Firebase Authentication triggers…”
   • [claimed-docs] “Cloud Functions now has experimental support for Dart. Flutter developers can now write both their frontend and backend in a single language…”
   • [claimed-docs] “Experimental: Cloud Functions now has experimental support for Dart. Flutter developers can now write both their frontend and backend in a s…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence describes Convex's reactive query model (queries automatically re-run when underlying data changes) and HTTP endpoints for calling functions, but there is no mention of user-definable rules, triggers, cron jobs, or scheduled/event-driven actions that a user could configure to fire automatically on arbitrary events. Missing for 10: any documentation of scheduled functions, cron/triggers, or a rule-definition mechanism for automated actions on events.

   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”
   • [community] “Convex engineer (james_cowling) on query invalidation: 'We track the readset for any active subscription. When a new write transaction commi…”
   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Firebase
   Firebase~partialcommunity6/10

   Firebase docs confirm Cloud Functions can be triggered by Cloud Scheduler jobs, enabling recurring/scheduled workflows (firebase-docs-7, firebase-docs-29), but this relies on the external Cloud Scheduler service rather than a native, first-class 'scheduled job' primitive within Firebase itself, and there is only one high-level doc mention with no setup detail or independent validation of current experience. An older community comment even flagged the historical absence of scheduled-task support as a pain point, suggesting this capability was a later addition rather than a mature core feature. missing for 10: dedicated documentation/tutorial on defining a scheduled function end-to-end, independent/hands-on confirmation that scheduling works reliably today, and any AI-native/agent-specific workflow scheduling support.

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “The functions you write can respond to events generated by various Firebase and Google Cloud features, from Firebase Authentication triggers…”
   • [community] “I have built apps with firebase in the past and the feature I missed the most was performing scheduled tasks on the database... AWS Lambda w…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence pack covers Convex's reactive database, auth, CLI, MCP server, and self-hosting, but contains no mention of cron jobs, scheduled functions, or recurring workflow scheduling capabilities, which is a plausible and often-touted Convex feature but is absent from this evidence set.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   Firebase—none0/10

   Firebase's evidence describes Cloud Functions, Security Rules, and CLI deployment, but nothing documents version history, review workflows, or rollback specifically for these 'automations' (functions/rules/triggers). Missing for 10: documented versioning/rollback of Cloud Functions or Security Rules, review/approval workflow, and any audit trail for automation changes.

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”

   proof ↗⚑ flag

   Convex—none0/10

   Convex's docs describe deployments, CLI commands (deploy, logs, insights), and self-hosting, but there is no evidence of any built-in versioning, review, or rollback mechanism for functions/automations — deployments appear to be driven by git-based code pushes with no rollback tooling mentioned. missing for 10: deployment version history, rollback command, and any review/approval workflow for changes.

   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “`npx convex insights` — Show health insights for your deployment”
   • [claimed-docs] “`npx convex logs` — Watch logs from your deployment”

   proof ↗⚑ flag

Database

1. developerConnect to the underlying database with standard clients and ORMs via a connection string

   weight 2 · round to Firebase
   Firebase~partialclaimed4/10

   Firebase's Firestore Enterprise edition offers a MongoDB-compatible API, letting developers reuse existing MongoDB drivers/tools/ORM ecosystem, which partially satisfies 'standard clients and ORMs' — but this applies only to the Enterprise edition, not the default Firestore or Realtime Database, and no connection-string mechanism is documented anywhere in the evidence pack. Missing for 10: explicit connection-string documentation, ORM support for the standard (non-Enterprise) Firestore/Realtime DB products, and independent/hands-on confirmation that MongoDB drivers actually connect successfully.

   • [claimed-docs] “Cloud Firestore offers a MongoDB-compatible API. You can use existing MongoDB application code, drivers, tools, and the open-source ecosyste…”
   • [claimed-docs] “You can use existing MongoDB application code, drivers, tools, and the open-source ecosystem of MongoDB integrations with Cloud Firestore in…”
   • [claimed-docs] “Cloud Firestore offers a MongoDB-compatible API. You can use existing MongoDB application code, drivers, tools, and the open-source ecosyste…”

   proof ↗⚑ flag

   Convex—none0/10

   Convex is a TypeScript-native document database with its own query functions and explicitly states 'no need to write any SQL' (convex-docs-2), and self-hosting docs only mention using external stores like Postgres/Neon as backing infra, not exposing Convex data via standard connection strings or ORMs. No evidence of ODBC/JDBC/SQL client or ORM connection-string support is present anywhere in the pack.

   • [claimed-docs] “There is nothing to set up and no need to write any SQL. Just use JavaScript to express your app's needs.”
   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”

   proof ↗⚑ flag

2. developerProvision a managed database and read/write it from client and server SDKs

   weight 3 · round to Convex
   Firebase✓fullcommunity8/10

   Firebase offers managed NoSQL databases (Cloud Firestore, Realtime Database) with official client SDKs for web/mobile and Admin SDK for server-side access, backed by docs on data sync, offline caching, and security rules, plus CLI/GitHub tooling for data interaction; community hands-on reports confirm fast, real-time read/write from clients and servers. Missing for 10: independent benchmark on server SDK write/read latency, and community notes cite real limitations (query features, count queries, historical offline-persistence gaps) that keep it from a perfect score.

   • [claimed-docs] “Store and sync app data at global scale without managing servers.”
   • [claimed-docs] “Your queries can include multiple, chained filters and combine filtering and sorting.”
   • [claimed-docs] “Cloud Firestore caches data that your app is actively using, so the app can write, read, listen to, and query data even if the device is off…”
   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [claimed-docs] “Firebase Security Rules leverage extensible, flexible configuration languages to define what data your users can access for Realtime Databas…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [community] “We were one of the first hundred users to join Firebase (ID:68) and I remember how easy it was to add real time notifications to one of my p…”
   • [community] “We used the original Firebase database product to build socrates.io 3.5 years ago, and I remember getting it running in a few hours.”
   • [community] “I've had only good experiences with firebase. They added an HTTP api, web hosting, multiple security rule preprocessors (pain point), and go…”
   • [community] “How do the querying features compare to Firebase? Firebase is notorious for having an unintuitive lack of server-side query options when you…”
   • [community] “When will it support a count query? Now to be able to count number of children I have to download all the data. Count is such an important f…”
   • [community] “So, still no offline persistence for JS. What a huge disappointment.”

   proof ↗⚑ flag

   Convex✓fullcommunity9/10

   Convex is a managed reactive database with no-setup provisioning (npm create convex@latest), automatic table creation, and client/server SDKs across React, Next.js, Remix, Vue, Svelte, React Native etc., plus HTTP endpoints for server-side access; ACID transactions and real-time sync are documented, and community/HN commentary corroborates the reactivity model internals. missing for 10: no independent hands-on benchmark of read/write latency or large-scale production usage report beyond docs and one HN thread.

   • [claimed-docs] “Convex is the open source, reactive database where queries are TypeScript code running right in the database.”
   • [claimed-docs] “There is nothing to set up and no need to write any SQL. Just use JavaScript to express your app's needs.”
   • [claimed-docs] “Your Convex deployment contains tables that hold your app's data. Initially, your deployment contains no tables or documents. Each table spr…”
   • [claimed-docs] “Real-time sync so your users instantly see the latest data”
   • [claimed-docs] “ACID transactions so concurrent writes never corrupt your data”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”
   • [claimed-docs] “Using your favorite frameworks: * React * Next.js * Remix * TanStack Start * React Native * Vue * Nuxt * Svelte”
   • [claimed-docs] “Start a new Convex project![...]`npm create convex@latest`”
   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”

   proof ↗⚑ flag

3. developerExpress relational queries with joins, constraints, and transactions

   weight 2 · round to Convex
   Firebase—none0/10

   Firebase's Firestore/Realtime Database are NoSQL document stores; evidence shows only chained filter/sort queries (firebase-docs-2) and a MongoDB-compatible API option (firebase-docs-4), with no mention of relational joins or multi-document transactions, and community evidence explicitly calls out the lack of server-side query capability (firebase-comm-4) and missing features like count queries (firebase-comm-16). No documentation of join support or transaction semantics appears in the pack.

   • [claimed-docs] “Your queries can include multiple, chained filters and combine filtering and sorting.”
   • [claimed-docs] “Cloud Firestore offers a MongoDB-compatible API. You can use existing MongoDB application code, drivers, tools, and the open-source ecosyste…”
   • [community] “How do the querying features compare to Firebase? Firebase is notorious for having an unintuitive lack of server-side query options when you…”
   • [community] “When will it support a count query? Now to be able to count number of children I have to download all the data. Count is such an important f…”

   proof ↗⚑ flag

   Convex~partialcommunity4/10

   Convex explicitly forgoes SQL and relational joins ('no need to write any SQL'), instead letting developers express multi-read/compute logic in TypeScript query functions (convex-comm-2) and enforcing ACID transactions (convex-docs-12) and optional schema shape validation (convex-docs-3). There is no documented declarative join operator or relational constraint system (foreign keys, uniqueness enforcement) — joins/constraints must be hand-coded in application logic rather than expressed as first-class relational queries. missing for 10: native join syntax/operator, declarative relational constraints (foreign keys/uniqueness), independent verification of complex multi-table query patterns.

   • [claimed-docs] “There is nothing to set up and no need to write any SQL. Just use JavaScript to express your app's needs.”
   • [claimed-docs] “Though optional, schemas ensure that your data looks exactly how you want.”
   • [claimed-docs] “ACID transactions so concurrent writes never corrupt your data”
   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”

   proof ↗⚑ flag

Realtime

1. developerBuild offline-capable clients whose local writes sync automatically on reconnect

   weight 2 · round to Firebase
   Firebase✓fullcommunity7/10

   Firestore docs explicitly describe local caching and offline write/read/sync capability that reconciles when connectivity returns, directly matching the story (firebase-docs-3). Confidence is tempered by an older community report claiming lack of JS offline persistence and by the absence of independent, recent hands-on corroboration of sync behavior. missing for 10: independent/hands-on confirmation of reconnect-sync behavior, and clarification on which SDKs currently support offline persistence.

   • [claimed-docs] “Cloud Firestore caches data that your app is actively using, so the app can write, read, listen to, and query data even if the device is off…”
   • [community] “So, still no offline persistence for JS. What a huge disappointment.”

   proof ↗⚑ flag

   Convex—none0/10

   Convex's evidence pack focuses on real-time reactive sync, ACID transactions, and cloud/self-hosted deployment, but nothing describes offline support, local persistence, or conflict-resolution/sync-on-reconnect for offline writes. Convex's model is explicitly server-driven reactivity (queries re-run on server-side data changes), which is a different capability than offline-first local writes.

   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”
   • [claimed-docs] “Real-time sync so your users instantly see the latest data”
   • [claimed-docs] “It makes it easy to build and scale dynamic live-updating apps.”

   proof ↗⚑ flag

2. developerTrack user presence and broadcast ephemeral state between connected clients

   weight 1 · round drawn
   Firebase~partialcommunity4/10

   Firebase's Realtime Database is built for syncing live data across connected clients, and community evidence describes real-time multi-client state sync (whiteboarding with synced positions, real-time notifications), which supports ephemeral broadcast use cases. However, the evidence pack never explicitly documents Firebase's presence-detection features (onDisconnect, .info/connected) which are the canonical mechanism for this story. Missing for 10: explicit docs on presence detection/onDisconnect API, independent verification of presence tracking specifically (not just generic realtime sync).

   • [claimed-docs] “Store and sync app data at global scale without managing servers.”
   • [community] “I built a real time whiteboarding app for teachers over 10 years ago on the backbone of the original Firebase service. It was so fast I was …”
   • [community] “We were one of the first hundred users to join Firebase (ID:68) and I remember how easy it was to add real time notifications to one of my p…”

   proof ↗⚑ flag

   Convex~partialcommunity4/10

   Convex's reactive query/mutation model and real-time sync primitives (automatic re-run of queries on data change, ACID mutations) provide the underlying building blocks needed to implement presence and ephemeral broadcast patterns, but the evidence pack contains no explicit presence feature, example, or component demonstrating this use case. Missing for 10: a documented presence/broadcast component or example, guidance on ephemeral (non-persisted) state handling, and TTL/expiry mechanisms for stale presence data.

   • [claimed-docs] “Real-time sync so your users instantly see the latest data”
   • [claimed-docs] “It makes it easy to build and scale dynamic live-updating apps.”
   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”
   • [community] “Convex engineer (james_cowling) on query invalidation: 'We track the readset for any active subscription. When a new write transaction commi…”
   • [claimed-docs] “Convex Components are sandboxed, open-source building blocks for your app. They let you add complex functionality to your app without implem…”

   proof ↗⚑ flag

3. developerSubscribe to live data changes so my UI updates in real time without polling

   weight 3 · round to Convex
   Firebase✓fullcommunity7/10

   Firebase's core value proposition includes real-time data sync — docs confirm apps can 'write, read, listen to, and query data' even offline, and multiple independent developers describe building live-updating apps (real-time whiteboard, real-time notifications, live sync across clients) confirming push-based updates rather than polling. missing for 10: explicit documentation of the onSnapshot/listener API surface and any first-party performance benchmarks for real-time delivery.

   • [claimed-docs] “Cloud Firestore caches data that your app is actively using, so the app can write, read, listen to, and query data even if the device is off…”
   • [community] “I built a real time whiteboarding app for teachers over 10 years ago on the backbone of the original Firebase service. It was so fast I was …”
   • [community] “We were one of the first hundred users to join Firebase (ID:68) and I remember how easy it was to add real time notifications to one of my p…”
   • [community] “We used the original Firebase database product to build socrates.io 3.5 years ago, and I remember getting it running in a few hours.”

   proof ↗⚑ flag

   Convex✓fullcommunity9/10

   Convex is built around reactive queries that automatically re-run and push updates to clients when underlying data changes, with first-party docs and detailed engineering explanations of the readset/writeset invalidation mechanism confirming no polling is used. Independent community corroboration from Convex engineers and outside commenters backs the reactivity model as real and functioning. Missing for 10: independent third-party benchmark or large-scale production case study explicitly measuring real-time update latency/reliability at scale.

   • [claimed-docs] “Real-time sync so your users instantly see the latest data”
   • [claimed-docs] “It makes it easy to build and scale dynamic live-updating apps.”
   • [community] “Convex explains reactivity model: 'there is no polling going on here - the query only reruns when the data dependencies change server-side d…”
   • [community] “Convex co-founder (sujayakar) explains internals: 'we entirely re-run the javascript function whenever we detect any of its inputs change...…”
   • [community] “Convex engineer (james_cowling) on query invalidation: 'We track the readset for any active subscription. When a new write transaction commi…”
   • [community] “Outside commenter praising the design: 'I like the model of the full function becomes the point of reactivity. It's very different than Fire…”

   proof ↗⚑ flag

Search

1. developerRun full-text search over my data without wiring up an external search service

   weight 2 · round drawn
   Firebase—none0/10

   The evidence shows Cloud Firestore supports filtering/sorting queries and vector (KNN) similarity search for embeddings, but nothing indicates native full-text search over string fields; Firestore is well known for requiring an external service (e.g., Algolia/Elasticsearch) for text search, and community comments even complain about limited query capabilities. No documentation or hands-on evidence shows a built-in full-text search feature.

   • [claimed-docs] “Your queries can include multiple, chained filters and combine filtering and sorting.”
   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches”
   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches using the following techniques”
   • [claimed-docs] “This page shows you how to use Cloud Firestore to perform K-nearest neighbor (KNN) vector searches using the following techniques: Store vec…”
   • [community] “How do the querying features compare to Firebase? Firebase is notorious for having an unintuitive lack of server-side query options when you…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence pack repeatedly documents Convex's vector search for embeddings-based similarity, but contains no mention of a full-text/keyword search index feature or API for text search without external tooling. Missing for 10: any docs reference to a full-text search index, search() query API, or tokenization/ranking behavior.

   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector... enable you to provide useful context to LLMs for AI powere…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector. Typically, vectors will be embeddings which are numerical re…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector... enable you to provide useful context to LLMs for AI powere…”
   • [claimed-docs] “Vector search allows you to find Convex documents similar to a provided vector.”

   proof ↗⚑ flag

1. developerRun functions automatically in response to database or auth events

   weight 2 · round to Firebase
   Firebase✓fullclaimed9/10

   Cloud Functions for Firebase is explicitly documented as a serverless framework that runs backend code automatically in response to background events, HTTPS requests, Admin SDK actions, or scheduler jobs, including Firebase Authentication triggers and Cloud Storage/Firestore triggers. This directly matches the story of running functions in response to database/auth events. missing for 10: independent hands-on report specifically confirming database/auth trigger reliability (community evidence focuses on other pain points, not this specific capability).

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “The functions you write can respond to events generated by various Firebase and Google Cloud features, from Firebase Authentication triggers…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence describes Convex's reactive query model (queries re-run when underlying data changes) and HTTP endpoints for calling functions, but there is no documentation of database/auth event triggers (e.g., 'on insert', 'on user created') that automatically invoke backend functions. Reactivity for client queries is a different mechanism than server-side function triggers implied by the story.

   ⚑ flag

2. developerDeploy server-side functions invoked by HTTP or SDK calls without managing servers

   weight 3 · round to Firebase
   Firebase✓fullclaimed9/10

   Cloud Functions for Firebase is explicitly documented as a serverless framework to run backend code triggered by HTTPS requests, Admin SDK/client SDK calls, or background events, with one-command CLI deployment and automatic scaling. Missing for 10: independent hands-on corroboration of production-scale reliability of Functions specifically (community evidence mostly discusses Firestore/Auth/pricing rather than Functions usage).

   • [claimed-docs] “Cloud Functions for Firebase is a serverless framework that lets you automatically run backend code in response to events triggered by backg…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [claimed-docs] “The functions you write can respond to events generated by various Firebase and Google Cloud features, from Firebase Authentication triggers…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”

   proof ↗⚑ flag

   Convex✓fullclaimed8/10

   Convex functions (queries, mutations, actions) are deployed serverlessly and can be invoked via SDK calls or exposed as public HTTP endpoints, with no server management required — the platform handles deployment, scaling, and infrastructure. Docs confirm public HTTP endpoints for calling functions and SDK-based invocation is core to the product. missing for 10: independent hands-on benchmarking of production HTTP invocation latency/scaling behavior, and more detail on action-specific server-side execution guarantees beyond docs claims.

   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, a…”

   proof ↗⚑ flag

Ai provisioning

1. ai-native userHave an agent stand up a new backend — schema, auth, and policies — headlessly from the CLI in a script

   weight 3 · round to Firebase
   Firebase~partialprobed6/10

   Firebase CLI (firebase-tools) supports scripted, headless deployment of Firestore/Realtime Database security rules, Cloud Functions, and Auth user import/export, and the MCP server also exposes project/auth/data management to agents, covering schema+auth+policies largely from the command line. However, there's no single documented 'init a full backend' one-shot command evidenced, and evidence doesn't show a non-interactive schema-creation flow (Firestore is schemaless, so 'schema' setup maps to rules/indexes only). missing for 10: a documented fully non-interactive scripted bootstrap command chaining project creation, schema/indexes, auth, and rules; independent hands-on confirmation of headless end-to-end setup.

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Import/Export users into/from Firebase Auth”
   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [claimed-docs] “Firebase Security Rules leverage extensible, flexible configuration languages to define what data your users can access for Realtime Databas…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”

   proof ↗⚑ flag

   Convex~partialprobed5/10

   Convex's CLI (`npx convex dev/run/import/deploy`) and code-first schema/auth model mean an agent could script much of a backend setup, and the MCP server lets agents interact with a deployment programmatically. However, there is no documented example of a fully headless script that provisions auth (Clerk/WorkOS typically require external dashboard setup) and authorization policies end-to-end without manual/interactive steps. Missing for 10: a documented headless script or MCP flow that configures auth providers and authorization policies (not just schema/functions) without human interaction, and evidence this is done end-to-end in practice.

   • [claimed-docs] “Clerk has great Next.js and React Native support”
   • [claimed-docs] “you can implement auth directly in Convex with the Convex Auth library... helps you build a custom sign-up/sign-in flow via social identity …”
   • [claimed-docs] “Clerk has great Next.js and React Native support ... WorkOS AuthKit is built for B2B apps ... Auth0 is more established with more bells and …”
   • [claimed-docs] “Convex doesn't need an opinionated authorization framework like RLS, which is required in client oriented databases like Firebase or Supabas…”
   • [claimed-docs] “which is required in client oriented databases like Firebase or Supabase. This flexibility lets you build and use an authorization framework…”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “Start a new Convex project![...]`npm create convex@latest`”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [probe] “official MCP server documented at https://docs.convex.dev/ai/convex-mcp-server”

   proof ↗⚑ flag

Local

1. developerRun the whole backend stack locally with an emulator or CLI before deploying

   weight 3 · round to Firebase
   Firebase✓fullprobed8/10

   Firebase's Local Emulator Suite explicitly supports running Firestore, Realtime Database, Storage, Auth, Hosting, Functions, Pub/Sub, and Extensions locally for integration testing without touching production, and the firebase-tools CLI supports running a local hosting server and interacting with data/deploying. This directly matches the story of running the whole backend stack locally before deploying, with unit-test support via mocha also documented. Missing for 10: independent/hands-on verification of full-suite parity beyond docs, and no community corroboration specifically praising the emulator suite's completeness.

   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [claimed-docs] “This means you can connect your app directly to these emulators to perform integration testing or QA without touching production data.”
   • [claimed-docs] “Unit Tests: using the Firebase Test SDK, you can write unit tests in Node.js using the mocha test runner.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”

   proof ↗⚑ flag

   Convex~partialclaimed5/10

   Convex's standard CLI workflow (`npx convex dev`) watches your filesystem and pushes changes, but pushes to a cloud-hosted 'dev deployment' rather than a fully local emulator (convex-docs-6, convex-docs-17). Separately, Convex offers self-hosting where you 'run the Convex backend on your own servers' with 'the same fully up-to-date code the cloud service uses,' which could be used to run the whole stack locally before deploying to production (convex-docs-8, convex-docs-19, convex-gh-1), but the docs frame this as an alternative deployment target rather than an explicit local pre-deploy emulator/test loop. Missing for 10: explicit documentation of a local emulator mode built into the standard dev CLI workflow, and hands-on/community confirmation that self-hosted mode is commonly used as a local pre-deploy sandbox.

   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Firebase
   Firebase~partialprobed6/10

   Firebase ships extensive first-party APIs/SDKs (Firestore, Auth, Functions, Rules) plus a CLI (firebase-tools) that can deploy, manage hosting, interact with database data, and import/export Auth users, and an official MCP server that lets AI tools create/manage projects, manage Auth users, and work with Firestore data — strong evidence of broad API/CLI parity with console actions. However, there is no explicit documentation or independent confirmation that *every* console capability (e.g., analytics/Gemini insights, billing, project-level admin settings) is exposed via API/CLI, and probes show no OpenAPI spec or llms.txt is published, weakening claims of full programmatic parity. Missing for 10: explicit full-parity documentation, independent hands-on confirmation that all UI actions map to API/CLI, and a published OpenAPI/machine-readable spec.

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site”
   • [github] “Import/Export users into/from Firebase Auth”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “Deploy your JavaScript, TypeScript, or Python code to our servers with one command from the command line. After that, Firebase automatically…”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”
   • [probe] “official CLI documented at https://firebase.google.com/docs/cli?hl=en”
   • [probe] “PROBE llms.txt: HTTP 404 at https://firebase.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://firebase.google.com/openapi.json, https://firebase.google.com/swagger.json, https://firebase…”

   proof ↗⚑ flag

   Convex~partialprobed5/10

   Convex exposes deployment functions via HTTP API and offers a CLI (run, import, logs, insights) plus an MCP server for AI agents to interact with deployments, showing broad but not total API/CLI parity with the dashboard UI. There's no explicit documentation claiming full UI/API parity, and probes found no OpenAPI spec, suggesting some dashboard-only features (e.g., visual data browsing, deployment settings) may lack a documented API equivalent. missing for 10: explicit parity statement, full OpenAPI/reference coverage, evidence that all dashboard actions (schema editing, table browsing, settings) are scriptable via API/CLI.

   • [claimed-docs] “The public functions that define a deployment are exposed at public HTTP endpoints.”
   • [claimed-docs] “These HTTP endpoints allow you to call Convex functions and get the result as a value.”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”
   • [claimed-docs] “`npx convex import` — Import data from a file to your deployment”
   • [claimed-docs] “`npx convex insights` — Show health insights for your deployment”
   • [claimed-docs] “`npx convex logs` — Watch logs from your deployment”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.convex.dev/openapi.json, https://docs.convex.dev/swagger.json, https://docs.convex.dev/…”
   • [probe] “official CLI documented at https://docs.convex.dev/cli/overview”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Convex
   Firebase!disputedcontradicted3/10

   Firebase CLI documents import/export of Auth users (open JSON) and one user notes deliberately keeping Firestore as a plain JSON store for portability, but there is no documented open-format export path for Firestore, Storage, or Security Rules, and multiple community accounts explicitly describe painful lock-in ('keenly aware of the cost of lock-in', 'need to reimplement storage rules — an absolute pain', 'the lock-in effect is super bad') when trying to migrate away. Missing for 10: comprehensive documented export of Firestore/Storage/Rules in open formats, first-party migration tooling, and independent confirmation that leaving is frictionless.

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Import/Export users into/from Firebase Auth”
   • [community] “I use Firebase Database but keep it arms length by avoiding any of the proprietary features it offers. I use it exclusively as a JSON store …”
   • [community] “My app is currently built on top of Firebase but I'm keenly aware of the cost of lock-in as traffic escalates.”
   • [community] “Besides the pricing, the other painful thing about Firebase are the storage rules. If I switch serverless I need to reimplement them — an ab…”
   • [community] “After being both delighted and frustrated about Firebase I decided that something must be done. The developer experience on Firebase is awes…”

   proof ↗⚑ flag

   Convex~partialclaimed5/10

   Convex documents open-source self-hosting (same backend as cloud) and an `npx convex import` CLI command, suggesting data portability and no vendor lock-in, but the evidence pack never documents an explicit data-export command or open export format (e.g., JSON/CSV dump) for leaving the platform. missing for 10: documented export command/tool, explicit open-format export (JSON/CSV), independent confirmation of a full data-export workflow.

   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [claimed-docs] “`npx convex import` — Import data from a file to your deployment”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Convex
   Firebase~partialclaimed3/10

   Evidence shows firebase-tools (the CLI) is hosted on a public GitHub repo, implying it is open source, but the core Firebase backend/service (Firestore, Auth, Functions runtime) is proprietary and no license or full source is documented for the platform itself. missing for 10: explicit open-source license statement, source availability for the core backend/service, independent confirmation of license terms for firebase-tools.

   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site”
   • [github] “Import/Export users into/from Firebase Auth”

   proof ↗⚑ flag

   Convex✓fullclaimed8/10

   Convex explicitly documents itself as open source, with a public GitHub repo (get-convex/convex-backend) for the self-hosted backend containing 'the same fully up-to-date code the cloud service uses,' and Convex Components are described as open-source building blocks — giving AI-native users direct access to readable source under an open license. missing for 10: explicit statement of the specific open-source license terms and independent confirmation of license permissiveness.

   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, a…”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”
   • [claimed-docs] “Convex Components are sandboxed, open-source building blocks for your app. They let you add complex functionality to your app without implem…”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Convex
   Firebase—none0/10

   Firebase is a fully-managed, closed Google Cloud service with no self-hosted/on-premise deployment option documented anywhere in the evidence; the emulator suite is explicitly for local testing/QA, not production self-hosting, and community comments highlight lock-in concerns rather than any self-hosting path.

   • [claimed-docs] “This means you can connect your app directly to these emulators to perform integration testing or QA without touching production data.”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [community] “My app is currently built on top of Firebase but I'm keenly aware of the cost of lock-in as traffic escalates.”
   • [community] “After being both delighted and frustrated about Firebase I decided that something must be done. The developer experience on Firebase is awes…”

   proof ↗⚑ flag

   Convex✓fullclaimed8/10

   Convex explicitly supports self-hosting the open-source backend on your own servers, with documentation confirming it runs the same code as the cloud service and integrates with common infra (Neon, Fly.io, Postgres, RDS, Sqlite, etc.). Missing for 10: independent hands-on reports of self-hosting at scale in production and more detail on feature parity/limitations versus the cloud offering.

   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, a…”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Firebase—none0/10

   No evidence in the pack mentions data residency, region selection, or location settings for Firebase services (Firestore, Storage, Functions, etc.), even though Firebase/GCP products do typically allow region selection in reality. Absence of evidence for this applicable capability yields 'none'.

   ⚑ flag

   Convex—none0/10

   No evidence of region/data-residency selection controls in Convex's cloud offering; self-hosting is mentioned but that requires managing your own infrastructure rather than choosing a region within Convex's service, and no docs describe region pinning or residency options. missing for 10: any documentation of region/residency selection, data locality controls, or compliance-driven region choice in the managed cloud product.

   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, a…”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend”
   • [github] “Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.”
   • [claimed-docs] “Log streaming * Exception reporting * HIPAA/SOC 2 reports * Daily backups * Custom domains”

   proof ↗⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round to Convex
   Firebase—none0/10

   The evidence pack covers Firestore querying, security rules, auth, functions, and emulators, but contains no documentation of data retention policies, TTL/expiration settings, or deletion/export APIs for privacy compliance (e.g., GDPR-style user data deletion). No citations address controlling how long data is kept or how it can be purged.

   ⚑ flag

   Convex~partialclaimed4/10

   Convex offers self-hosting (full control over your own data infrastructure) and lists HIPAA/SOC 2 reports plus daily backups as enterprise features, which implies some data governance controls, but there is no explicit documentation of user-facing data retention policies, deletion APIs, or right-to-erasure workflows. missing for 10: explicit data deletion/retention API or policy docs, GDPR/right-to-erasure support, retention configuration options.

   • [claimed-docs] “you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, and contains the same fully up-to-date …”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend...”
   • [claimed-docs] “If you're excited about self-hosting, you can run the Convex backend on your own servers. Self-hosted Convex runs the open-source backend, a…”
   • [claimed-docs] “Log streaming * Exception reporting * HIPAA/SOC 2 reports * Daily backups * Custom domains”

   proof ↗⚑ flag

3. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Firebase—none0/10

   No evidence pack items mention telemetry, usage tracking, or an opt-out mechanism for Firebase's own tooling/services; only unrelated docs on Firestore, Auth, Functions, and pricing are present.

   ⚑ flag

   Convex—none0/10

   No evidence pack item discusses telemetry, usage analytics, or an opt-out mechanism in Convex CLI/backend/docs; self-hosting is offered but that's a deployment choice, not a documented telemetry toggle.

   ⚑ flag

Ai migrations

1. ai-native userLet an agent create and test schema changes in an isolated branch or preview environment before production

   weight 3 · round to Convex
   Firebase~partialprobed4/10

   Firebase's Local Emulator Suite lets developers (or an agent driving the CLI) test Firestore/Security Rules changes locally without touching production data, and the MCP server exposes Firestore project/data management to AI agents — together giving a rough isolated-testing story. However, Firestore is schemaless (no formal schema-migration concept) and there is no documented branch/preview-environment feature (e.g., a project 'branch' with automatic promotion) analogous to database branching tools. Missing for 10: explicit schema/migration versioning, a true branch/preview-environment workflow, and evidence of an agent autonomously provisioning/testing such a branch before production.

   • [claimed-docs] “This means you can connect your app directly to these emulators to perform integration testing or QA without touching production data.”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [claimed-docs] “An editor configured to use the Firebase MCP server can use its AI capabilities to help you: Create and manage Firebase projects, Manage you…”
   • [probe] “official MCP server documented at https://firebase.google.com/docs/ai-assistance/mcp-server?hl=en”

   proof ↗⚑ flag

   Convex~partialclaimed5/10

   Convex's CLI/dev deployment model (docs-6/17) automatically syncs schema changes to a separate dev deployment when developing, and the official MCP server explicitly blocks access to production deployments by default as a safety measure (docs-28), which together let an agent iterate on schema changes in an isolated, non-production environment. However, there is no explicit mention of a distinct 'branch' or 'preview environment' feature, nor documentation of testing/promotion workflow from that isolated environment into production. missing for 10: explicit preview/branch deployment feature, agent-driven promotion workflow from dev to production, independent corroboration of this workflow.

   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “By default, the MCP server cannot access production deployments. This is a safety measure to prevent accidental modifications to production …”
   • [claimed-docs] “The Convex Model Context Protocol (MCP) server provides several tools that allow AI agents to interact with your Convex deployment.”

   proof ↗⚑ flag

Migrations

1. developerManage schema changes as version-controlled migrations applied via the CLI or CI

   weight 3 · round to Convex
   Firebase—none0/10

   Firebase's CLI can deploy static config like Firestore security rules and indexes, but there is no evidence of a schema-migration framework (versioned, incremental migrations with up/down scripts) applied via CLI/CI; in fact a community report explicitly notes the lack of a business-logic layer makes schema changes 'extremely challenging' for deployed clients, underscoring the absence of this capability.

   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [github] “Deploy code and assets to your Firebase projects - Run a local web server for your Firebase Hosting site - Interact with data in your Fireba…”
   • [community] “The concern I've always had with Firebase is the lack of a business logic layer between clients and the database. This tends to force the bu…”

   proof ↗⚑ flag

   Convex~partialclaimed4/10

   Convex schemas are defined in code (schema.ts) and the CLI automatically pushes schema changes to a deployment when files change (convex-docs-6/17), which gives an implicit, version-controllable schema workflow, but the evidence never describes a dedicated migrations system (versioned migration files, up/down scripts) or explicit CI/CD deployment pipeline usage. missing for 10: explicit migration versioning/history tooling, documented CI integration for applying schema changes, rollback support.

   • [claimed-docs] “Though optional, schemas ensure that your data looks exactly how you want.”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “npx convex run <functionName> [args] — Run a public or internal Convex query, mutation, or action on your development deployment.”

   proof ↗⚑ flag

Type safety

1. developerGenerate typed client code (e.g. TypeScript types) from my schema automatically

   weight 2 · round to Convex
   Firebase—none0/10

   No evidence of Firebase generating typed client code/TypeScript types from a schema; docs cover Firestore, Auth, Functions, emulators, security rules, and MCP/Gemini AI features but nothing about automatic type generation from schema.

   ⚑ flag

   Convex✓fullclaimed8/10

   Convex's CLI dev process watches schema/function changes and automatically updates generated TypeScript types in convex/_generated, giving end-to-end type safety from schema to client code without manual codegen commands. This is well documented in official docs and reinforced by the 'end-to-end type safety' marketing claim. Missing for 10: independent/hands-on developer confirmation of the generated types workflow beyond first-party docs.

   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment and the generated…”
   • [claimed-docs] “Watches the local filesystem. When you change a function or the schema, the new versions are pushed to your dev deployment”
   • [claimed-docs] “End-to-end type safety so agent hallucinations are caught before they ship”

   proof ↗⚑ flag

Access control

1. developerRestrict data access per user with row-level security policies or security rules

   weight 3 · round to Firebase
   Firebase✓fullcommunity8/10

   Firebase Security Rules are extensively documented as the mechanism to restrict data access per user across Firestore, Realtime Database, and Cloud Storage, with granular, expression-based rule languages, and community evidence corroborates real-world use (e.g., failed attempts blocked by rules, separation of auth logic from data access). missing for 10: no independent hands-on audit of rule robustness/edge cases, and community notes rules can be painful to maintain/reimplement, slightly denting polish.

   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [claimed-docs] “Firebase Security Rules leverage extensible, flexible configuration languages to define what data your users can access for Realtime Databas…”
   • [claimed-docs] “You can write simple or complex rules that protect your app's data to the level of granularity that your specific app requires.”
   • [community] “One of the things I find quite nice about firebase is the powerful separation between data retrieval/update logic and the enforcement of acc…”
   • [community] “"This includes failed attempts which are blocked by their security rules." Ouch!”
   • [community] “Besides the pricing, the other painful thing about Firebase are the storage rules. If I switch serverless I need to reimplement them — an ab…”

   proof ↗⚑ flag

   Convex~partialclaimed4/10

   Convex explicitly rejects an RLS-style authorization framework, instead relying on developers to write access checks manually inside each query/mutation function ('Convex doesn't need an opinionated authorization framework like RLS... This flexibility lets you build and use an authorization framework for your needs'). This means per-user data restriction is possible but must be hand-coded per function rather than declared as reusable security rules/policies, unlike a dedicated RLS feature. missing for 10: no built-in declarative row-level security policy syntax, no documentation of a reusable rules layer, no independent/hands-on evidence of implementing or testing such access control.

   • [claimed-docs] “Convex doesn't need an opinionated authorization framework like RLS, which is required in client oriented databases like Firebase or Supabas…”
   • [claimed-docs] “which is required in client oriented databases like Firebase or Supabase. This flexibility lets you build and use an authorization framework…”

   proof ↗⚑ flag

Data protection

1. platform-engineerRely on automated backups and point-in-time recovery for my data

   weight 2 · round to Convex
   Firebase—none0/10

   No evidence in the pack mentions automated backups or point-in-time recovery for Firestore/Realtime Database; only security rules, querying, offline caching, and emulator suite are documented. This is a plausible axis for a database/backend platform, so absence of evidence yields 'none'.

   ⚑ flag

   Convex~partialclaimed3/10

   The pricing page lists 'Daily backups' as an included feature on paid plans, confirming some automated backup capability, but there is no mention of point-in-time recovery, backup retention windows, restore process, or how backups work for self-hosted deployments. Missing for 10: point-in-time recovery details, backup restore/testing docs, retention policy specifics, and independent verification of backup reliability.

   • [claimed-docs] “Log streaming * Exception reporting * HIPAA/SOC 2 reports * Daily backups * Custom domains”

   proof ↗⚑ flag

Files

1. developerUpload and serve user files with access rules and CDN-backed delivery

   weight 3 · round to Firebase
   Firebase~partialcommunity3/10

   Evidence only mentions 'Cloud Storage' in passing as one of the products covered by Firebase Security Rules and the Emulator Suite (firebase-docs-10, firebase-docs-18, firebase-docs-24), with community mentions of 'storage rules' as a pain point (firebase-comm-5, firebase-comm-8). There is no documentation in the pack describing file upload/download APIs, access-rule granularity for files, or CDN-backed delivery specifics. missing for 10: docs on Cloud Storage upload/download SDK, CDN delivery details, access-rule examples for file objects, independent corroboration of CDN performance.

   • [claimed-docs] “Use our flexible, extensible Firebase Security Rules to secure your data in Cloud Firestore, Firebase Realtime Database, and Cloud Storage.”
   • [claimed-docs] “Firebase Security Rules leverage extensible, flexible configuration languages to define what data your users can access for Realtime Databas…”
   • [claimed-docs] “The Firebase Local Emulator Suite is a set of advanced tools for developers looking to build and test apps locally using Cloud Firestore, Re…”
   • [community] “Besides the pricing, the other painful thing about Firebase are the storage rules. If I switch serverless I need to reimplement them — an ab…”
   • [community] “I'm a big fan of firebase and use it whenever I can. The reason it's appealing is the suite of tools and how well they work together for boo…”

   proof ↗⚑ flag

   Convex—none0/10

   The evidence pack contains no mention of file upload, file storage APIs, access-controlled file serving, or CDN-backed delivery anywhere in the Convex docs, CLI, or community citations provided. While file storage is a plausible axis for a backend platform, nothing in this evidence pack substantiates it.

   ⚑ flag

2. developerServe resized or transformed images from storage without running my own image pipeline

   weight 1 · round drawn
   Firebase—none0/10

   No evidence pack items mention Firebase Extensions for image resizing, Cloud Storage image transformation, or any built-in image pipeline capability; the pack covers Firestore, Auth, Functions, Rules, and MCP but nothing about serving resized/transformed images.

   ⚑ flag

   Convex—none0/10

   No evidence in the pack mentions Convex file storage supporting image resizing/transformation or any built-in image pipeline; storage-related evidence is entirely absent. This is a fair axis for a backend/storage platform, so lack of evidence yields 'none' rather than 'na'.

   ⚑ flag