framework-mcp

npm install npm run db:migrate npm run db:seed npm run build

npm run create-api-key -- "my laptop"

Connect tohttp://localhost:3000/mcpwith transport "Streamable HTTP" and set anAuthorization: Bearer <your-api-key>header in the connection settings. Confirm all 3 tools (ping,query_framework_doc,report_outcome) list and are callable.
- curl -fsSL agents.railway.com | shthenrailway login.
- From this repo:railway init(orrailway linkif a project already exists).
- Set env vars (dashboard, orrailway variable set KEY=value):DATABASE_URL(your Neonproductionbranch connection string, separate from your dev branch),API_KEY_PEPPER,NODE_ENV=production.
- railway up.
- In the Railway dashboard: Settings → Networking → Generate Domain. SetPUBLIC_HOSTNAMEto that domain (needed for the SDK's DNS-rebinding host check to allow real traffic).
- Runnpm run db:migrate && npm run db:seedonce against the productionDATABASE_URL(from your machine, pointed at the prod connection string).
- Create a production API key withnpm run create-api-key, pointed at the prodDATABASE_URL.

Maintainer/local fallback:npm run create-api-key -- "label".

{ "mcpServers": { "framework-mcp": { "type": "http", "url": "https://<your-railway-domain>/mcp", "headers": { "Authorization": "Bearer <your-api-key>" } } } }

- ping(message)- health check
- list_frameworks()- lists every framework/version covered, with entry counts - call this first if you don't know the exact slug/version to pass below
- query_framework_doc(framework, version, question)- look up a verified answer, returnsquery_id
- report_outcome(query_id, worked, note?)- log whether the returned answer actually worked

All entries verified 2026-08-22 against the official sources cited in each seed file underdb/seed/. To add a framework: create a newdb/seed/<slug>.jsonfollowing the existing files' shape, thennpm run db:seed(it picks up every*.jsonin that folder automatically).

Self-service signup live at/(email -> instant API key, one per email, IP rate-limited). Published to the official MCP Registry (registry.modelcontextprotocol.io) and submitted to mcpservers.org and Glama (both pending review). Not on Smithery (their OAuth-discovery scanner doesn't support simple static bearer-key auth) or mcp.so (no free listing tier).

Deferred (Stage B, not built yet): Stripe billing,plan_tier/credit_balance/ rate-limit-enforcement-per-key onapi_keys, scoring/ranking on feedback.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Assists AI developers with requirement clarification, module design, and technical architecture.

Provides AI assistants with a comprehensive, one-time analysis for complete codebase context and understanding.

The official Duck Framework MCP server provides AI assistants with rich, project-aware context for building applications using Duck Framework. It offers documentation retrieval, code guidance, API references, best practices, component discovery, and framework-specific recommendations to help developers generate high-quality Duck Framework projects faster and more accurately.

Integrates MATLAB with AI to execute code, generate scripts from natural language, and access documentation.

An AI-powered documentation server for code improvement and management, with Claude and Brave Search integration.

A collection of reference implementations for the Model Context Protocol (MCP), demonstrating how to give LLMs secure access to tools and data using Typescript and Python SDKs.

Automatic documentation updates from agents, and codebase conventions to reduce token usage.

AI agent readability scanner: 59 checks against the Vercel Spec, llmstxt.org, and agent-protocol manifests, with per-check fix guidance.

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .