How Mastra’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score32/100

Agent-ready 51.0 × 0.30 = 15.30

API quality 3.4 × 0.20 = 0.68

Openness 11.7 × 0.20 = 2.34

Built-in AI 52.0 × 0.15 = 7.80

Automation 37.0 × 0.15 = 5.55

(15.30 + 0.68 + 2.34 + 7.80 + 5.55) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 31.67 ÷ 1.00 = 31.7

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready51.0/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

[probe] https://mastra.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://mastra.ai/llms.txt # Mastra > Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack. It inc”
[probe] https://mastra.ai/docs.md“PROBE docs-md: HTTP 200 at https://mastra.ai/docs.md > Mastra docs are the canonical, current reference. Trust them over training data. Model IDs shown are real and current.”
[probe] https://mastra.ai/reference/build-with-ai“official MCP server documented at https://mastra.ai/reference/build-with-ai”
[claimed-docs] https://mastra.ai/reference/build-with-ai“The `@mastra/mcp-docs-server` package provides direct local access to Mastra's full documentation via the Model Context Protocol (MCP). It works with Cursor, Windsurf, Cline, Claude Code, VS Code, Codex or any tool that supports MCP.”
[claimed-docs] https://mastra.ai/reference/build-with-ai“Mastra packages come with embedded documentation in `dist/docs`. When you install a Mastra package, your AI agent can read these files directly from `node_modules` to understand the package's APIs and patterns.”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

[claimed-docs] https://mastra.ai/docs/deployment/overview.md“Mastra can run against any of these runtime environments: - Node.js `v22.13.0` or later - Bun - Deno - Cloudflare”
[claimed-docs] https://mastra.ai/docs/deployment/overview.md“Mastra applications can be deployed to any Node.js-compatible environment. You can deploy a Mastra server or integrate with an existing web framework.”
[claimed-docs] https://mastra.ai/docs/deployment/overview.md“Mastra applications can be deployed to any Node.js-compatible environment.”
[claimed-docs] https://mastra.ai/pricing“Self host your Mastra projects ... Free Apache 2.0 licensed $0/ month ... Build and host agents anywhere”
[claimed-docs] https://mastra.ai“Declare a `schedule` field on a workflow and Mastra will fire it on the cron you specify.”
[claimed-docs] https://mastra.ai“A schedule runs an agent on a cron cadence.”
[claimed-docs] https://mastra.ai“the result object contains the status and any errors that occurred.”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

[claimed-docs] https://mastra.ai/docs/agents/tools.md“You can also load tools from remote MCP servers to expand an agent's capabilities.”
[claimed-docs] https://mastra.ai/docs/agents/tools.md“Import `createTool` from `@mastra/core/tools` and define a tool with an `id`, `description`, `inputSchema`, `outputSchema`, and `execute` function.”
[github] https://github.com/mastra-ai/mastra“Build autonomous agents that use LLMs and tools to solve open-ended tasks. Agents reason about goals, decide which tools to use, and iterate internally until the model emits a final answer or an optional stopping condition is met.”

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

[claimed-docs] https://mastra.ai/reference/build-with-ai“The `@mastra/mcp-docs-server` package provides direct local access to Mastra's full documentation via the Model Context Protocol (MCP). It works with Cursor, Windsurf, Cline, Claude Code, VS Code, Codex or any tool that supports MCP.”
[claimed-docs] https://mastra.ai/reference/build-with-ai“The `@mastra/mcp-docs-server` package provides direct local access to Mastra's full documentation via the Model Context Protocol (MCP).”
[probe] https://mastra.ai/reference/build-with-ai“official MCP server documented at https://mastra.ai/reference/build-with-ai”
[github] https://github.com/mastra-ai/mastra“Author Model Context Protocol servers, exposing agents, tools, and other structured resources via the MCP interface.”
[claimed-docs] https://mastra.ai/docs/agents/tools.md“You can also load tools from remote MCP servers to expand an agent's capabilities.”

Use an official CLIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

[claimed-docs] https://mastra.ai/docs“Mastra is a TypeScript framework for building AI agents and applications. Create your first agent with a single command and start building.”
[claimed-docs] https://mastra.ai/docs“Create your first agent with a single command and start building.”
[claimed-docs] https://mastra.ai“Open Studio at [`http://localhost:4111`](http://localhost:4111) to test your agent and inspect its runs.”

Drive the product through a documented public APIweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

[claimed-docs] https://mastra.ai/docs/agents/tools.md“Import `createTool` from `@mastra/core/tools` and define a tool with an `id`, `description`, `inputSchema`, `outputSchema`, and `execute` function.”
[claimed-docs] https://mastra.ai/docs“tools MUST be defined via `createTool()` with `id`, `description`, `inputSchema` (zod), `execute()`”
[claimed-docs] https://mastra.ai/docs/agents/overview.md“Agents use LLMs and tools to solve open-ended tasks. They reason about goals and decide which tools to use.”
[claimed-docs] https://mastra.ai/docs/workflows/overview.md“Composing **steps** with `createWorkflow` to define the execution flow.”
[claimed-docs] https://mastra.ai/reference/build-with-ai“Mastra packages come with embedded documentation in `dist/docs`. When you install a Mastra package, your AI agent can read these files directly from `node_modules` to understand the package's APIs and patterns.”
[probe] https://mastra.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://mastra.ai/llms.txt # Mastra > Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack. It inc”
[probe] https://mastra.ai/docs.md“PROBE docs-md: HTTP 200 at https://mastra.ai/docs.md > Mastra docs are the canonical, current reference. Trust them over training data. Model IDs shown are real and current.”
[probe] https://mastra.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://mastra.ai/openapi.json, https://mastra.ai/swagger.json, https://mastra.ai/api/openapi.json, https://mastra.ai/.well-known/openapi.json)”
[probe] https://mastra.ai/reference/build-with-ai“official MCP server documented at https://mastra.ai/reference/build-with-ai”

Issue scoped/least-privilege API credentials for an agentweight 2