Convex

Connect an agent via an official MCP server G

Agent access

Drive the product through a documented public API G

Agent access

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

Plug MCP servers into this product so it can use their tools G

Agent access

Build against official SDKs G

Agent access

Point an agent at llms.txt or agent-oriented docs G

Agent access

Use an official CLI G

Agent access

Operate the product with natural-language commands G

Agentic features

Run the product headlessly / in CI for automation G

Agent access

Issue scoped/least-privilege API credentials for an agent G

Agent access

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

Explore an interactive API reference with runnable examples G

Api quality

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

Rely on versioned APIs with a documented deprecation policy G

Api quality

Subscribe to events via webhooks G

Agent access

Set up automations that run autonomously in the background G

Agentic features

Test against a sandbox environment without touching production data G

Api quality

Provision a managed database and read/write it from client and server SDKs C

Database

Subscribe to live data changes so my UI updates in real time without polling C

Realtime

Deploy server-side functions invoked by HTTP or SDK calls without managing servers C

Self-host the core product G

Store embeddings and run vector similarity search for AI features C

Vector

Add email/password and social OAuth sign-in with the platform SDK in minutes C

Authentication

Export all of my data in open formats and leave G

Have an agent stand up a new backend — schema, auth, and policies — headlessly from the CLI in a script C

Ai provisioning

Let an agent create and test schema changes in an isolated branch or preview environment before production C

Ai migrations

Run the whole backend stack locally with an emulator or CLI before deploying C

Local

Manage schema changes as version-controlled migrations applied via the CLI or CI C

Migrations

Restrict data access per user with row-level security policies or security rules C

Access control

Define rules that trigger actions automatically on events G

Prevent my data from being used to train AI models G

Upload and serve user files with access rules and CDN-backed delivery C

Files

Generate typed client code (e.g. TypeScript types) from my schema automatically C

Type safety

Read the product's source under an open license G

Do everything through the API that I can do in the UI G

Control data retention and deletion G

Express relational queries with joins, constraints, and transactions C

Database

Perform bulk operations across many items at once G

Rely on automated backups and point-in-time recovery for my data C

Data protection

Ask an AI assistant in the dashboard to write queries, debug errors, and explain my backend C

Ai assist

Build offline-capable clients whose local writes sync automatically on reconnect C

Realtime

Choose where my data is stored (region/residency) G

Connect to the underlying database with standard clients and ORMs via a connection string C

Database

Require MFA and enterprise SSO (SAML/OIDC) for my application users G

Authentication

Run full-text search over my data without wiring up an external search service C

Search

Opt out of telemetry and usage tracking G

Run functions automatically in response to database or auth events C

Schedule recurring jobs or workflows G

Track user presence and broadcast ephemeral state between connected clients C

Realtime

Version, review, and roll back my automations G

Serve resized or transformed images from storage without running my own image pipeline C

Files