Back to Browse

Framework MCP Server

Developer ToolsLow Risk10.0MCP RegistryRemote
Free

Server data from the Official MCP Registry

Verified, version-pinned answers about fast-moving frameworks for coding agents.

About

Verified, version-pinned answers about fast-moving frameworks for coding agents.

Remote endpoints: streamable-http: https://framework-mcp-production.up.railway.app/mcp

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (3 strong, 2 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.

Endpoint verified · Requires authentication · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Connect

Remote Plugin

No local installation needed. Your AI client connects to the remote endpoint directly.

Add this to your MCP configuration to connect:

{
  "mcpServers": {
    "io-github-81labsapps-ops-framework-mcp": {
      "url": "https://framework-mcp-production.up.railway.app/mcp"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

framework-mcp

A dependency currency-check layer for coding agents: a remote MCP server that gives coding agents (Claude Code, Cursor, etc.) verified, version-pinned answers about fast-moving frameworks - Expo, Next.js, Supabase, Prisma, and growing.

Why: LLM training data goes stale faster than framework release cycles. Agents keep re-guessing the same version-specific questions instead of checking a verified, version-pinned source. This server is that source - not a single-framework tool, but a general layer any coding agent can query before trusting what it "remembers" about a dependency's current behavior.

Stack

Node 24 + TypeScript, @modelcontextprotocol/sdk over Streamable HTTP transport (stateful, session-per-connection), Express, Postgres (pg), API-key auth via the SDK's own requireBearerAuth middleware.

Hosting: Railway (compute, ~$5/mo Hobby plan) + Neon (Postgres, free tier, branchable).

Local setup

  1. Create a free Neon account and project. Copy the connection string for a dev branch.
  2. cp .env.example .env and fill in DATABASE_URL (from Neon) and API_KEY_PEPPER (any long random string - generate one with node -e "console.log(require('crypto').randomBytes(32).toString('hex'))").
  3. Install, migrate, seed, build:
    npm install
    npm run db:migrate
    npm run db:seed
    npm run build
    
  4. Create yourself an API key:
    npm run create-api-key -- "my laptop"
    
    This prints the raw key once - save it, it's not recoverable.
  5. Run locally:
    npm run dev
    
    curl http://localhost:3000/health should return ok.

Verify with MCP Inspector

npx @modelcontextprotocol/inspector

Connect to http://localhost:3000/mcp with transport "Streamable HTTP" and set an Authorization: Bearer <your-api-key> header in the connection settings. Confirm all 3 tools (ping, query_framework_doc, report_outcome) list and are callable.

Deploy to Railway

  1. curl -fsSL agents.railway.com | sh then railway login.
  2. From this repo: railway init (or railway link if a project already exists).
  3. Set env vars (dashboard, or railway variable set KEY=value): DATABASE_URL (your Neon production branch connection string, separate from your dev branch), API_KEY_PEPPER, NODE_ENV=production.
  4. railway up.
  5. In the Railway dashboard: Settings → Networking → Generate Domain. Set PUBLIC_HOSTNAME to that domain (needed for the SDK's DNS-rebinding host check to allow real traffic).
  6. Run npm run db:migrate && npm run db:seed once against the production DATABASE_URL (from your machine, pointed at the prod connection string).
  7. Create a production API key with npm run create-api-key, pointed at the prod DATABASE_URL.

Get an API key

Self-service: visit https://framework-mcp-production.up.railway.app/, enter an email, get a key instantly (one active key per email, rate-limited).

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

Connect a remote client

In a Claude Code .mcp.json:

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

Tools

  • 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, returns query_id
  • report_outcome(query_id, worked, note?) - log whether the returned answer actually worked

Coverage

FrameworkVersionEntriesSource
Expo SDK54.0.020expo.dev/changelog/sdk-54
Next.js16.3.220nextjs.org/blog, nextjs.org/docs upgrade guide
Supabase (supabase-js)2.112.320supabase.com/changelog, GitHub releases
Prisma ORM7.9.120prisma.io/docs upgrade guide, prisma.io/changelog
Vercel AI SDK7.0.7720ai-sdk.dev migration guides, vercel.com/blog
Nuxt4.5.220nuxt.com/docs upgrade guide, nuxt.com/blog

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

Status

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 on api_keys, scoring/ranking on feedback.

Reviews

No reviews yet

Be the first to review this server!