Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Verified, version-pinned answers about fast-moving frameworks for coding agents.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http framework https://framework-mcp-production.up.railway.app/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"framework": {
"url": "https://framework-mcp-production.up.railway.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"framework": {
"type": "http",
"url": "https://framework-mcp-production.up.railway.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account 81labsapps-ops, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.3.0) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, zanadir
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Find what a repository's CI is missing, and which security checks cannot fail the build.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
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).
dev branch.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'))"). 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.
npm run dev
curl http://localhost:3000/health should return ok.
npx @modelcontextprotocol/inspector
Connect to http://localhost:3000/mcp with transport "Streamable HTTP" and set an Authorization: Bearer header in the connection settings. Confirm all 3 tools (ping, query_framework_doc, report_outcome) list and are callable.
curl -fsSL agents.railway.com | sh then railway login.railway init (or railway link if a project already exists).railway variable set KEY=value): DATABASE_URL (your Neon production branch connection string, separate from your dev branch), API_KEY_PEPPER, NODE_ENV=production.railway up.PUBLIC_HOSTNAME to that domain (needed for the SDK's DNS-rebinding host check to allow real traffic).npm run db:migrate && npm run db:seed once against the production DATABASE_URL (from your machine, pointed at the prod connection string).npm run create-api-key, pointed at the prod DATABASE_URL.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".
In a Claude Code .mcp.json:
{
"mcpServers": { "framework-mcp": { "type": "http", "url": "https:// /mcp", "headers": { "Authorization": "Bearer " } } } }
ping(message) - health checklist_frameworks() - lists every framework/version covered, with entry counts - call this first if you don't know the exact slug/version to pass belowquery_framework_doc(framework, version, question) - look up a verified answer, returns query_idreport_outcome(query_id, worked, note?) - log whether the returned answer actually worked| Framework | Version | Entries | Source |
|---|---|---|---|
| Expo SDK | 54.0.0 | 20 | expo.dev/changelog/sdk-54 |
| Next.js | 16.3.2 | 20 | nextjs.org/blog, nextjs.org/docs upgrade guide |
| Supabase (supabase-js) | 2.112.3 | 20 | supabase.com/changelog, GitHub releases |
| Prisma ORM | 7.9.1 | 20 | prisma.io/docs upgrade guide, prisma.io/changelog |
| Vercel AI SDK | 7.0.77 | 20 | ai-sdk.dev migration guides, vercel.com/blog |
| Nuxt | 4.5.2 | 20 | nuxt.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/ .json following the existing files' shape, then npm run db:seed (it picks up every *.json in 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 on api_keys, scoring/ranking on feedback.