SEODesk MCP Server
Provides a tool to retrieve Google PageSpeed Insights data for both mobile and desktop, enabling performance analysis of web pages.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SEODesk MCP ServerAnalyze the SEO of example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SEODesk MCP Server
A Remote MCP (Model Context Protocol) server that exposes the SEODesk SEO toolset to ChatGPT Apps and any other MCP-compatible client (Claude, Cursor, Codex, etc.).
Transport: Streamable HTTP (spec 2025-06-18) at
POST /mcpAuth: OAuth 2.1 with PKCE + Dynamic Client Registration (RFC 7591)
SDK:
@modelcontextprotocol/sdkRuntime: Node.js 20+
The Lovable frontend is untouched. ChatGPT talks to this MCP server; the frontend keeps talking to the existing Supabase Edge Functions. This server calls the same Edge Functions internally to fulfil tool calls.
Tools exposed
Tool | Purpose |
| Full on-page SEO analysis for a URL |
| Technical site audit (findings by category) |
| Google PageSpeed Insights (mobile + desktop) |
| Keywords, questions, clusters from a seed |
| AI-generated SEO |
| AI-generated meta descriptions |
| JSON-LD schema (Article, Product, FAQPage, …) |
| Backlink profile summary (requires provider key) |
| Content brief vs. a target keyword |
Related MCP server: Google Search Console MCP
Endpoints
Path | Description |
| MCP Streamable HTTP endpoint (requires |
| Liveness probe |
| Readiness probe |
| OAuth 2.0 AS metadata (RFC 8414) |
| MCP resource metadata (RFC 9728) |
| Dynamic Client Registration (RFC 7591) |
| Authorization endpoint (PKCE S256 required) |
| Token endpoint (auth code + refresh) |
Local development
cd mcp-server
cp .env.example .env # fill in values
npm install
npm run devSanity check:
curl http://localhost:3333/health
curl http://localhost:3333/.well-known/oauth-authorization-serverEnvironment variables
See .env.example. Required at minimum:
PUBLIC_BASE_URL— public HTTPS URL of this server (used as OAuth issuer).JWT_SECRET— long random string, signs access tokens.SUPABASE_URL,SUPABASE_ANON_KEY,SUPABASE_SERVICE_ROLE_KEY— to call SEODesk backend Edge Functions.LOVABLE_API_KEY— for AI-powered tools (meta/schema/optimizer).GOOGLE_PAGESPEED_API_KEY— optional (Edge Function can supply its own).
Deploy to Railway
Push this folder to a Git repo.
In Railway → New Project → Deploy from GitHub, pick the repo and set the root directory to
mcp-server.Add the env vars from
.env.exampleunder Variables.Railway auto-detects Node;
railway.tomlsets the healthcheck to/health.After deploy, set
PUBLIC_BASE_URLandOAUTH_ISSUERto the generated HTTPS domain (e.g.https://seodesk-mcp.up.railway.app) and redeploy.
Deploy to Cloudflare Workers
The MCP SDK targets Node's http module, so the simplest CF path is to deploy
this Node app to Cloudflare Containers (or Fly.io / Render) rather than a
plain Worker. If you want a pure Workers deployment, port the two files
src/index.js and src/oauth.js onto itty-router + @modelcontextprotocol/sdk's
Web-Standard transport — the tool definitions in src/tools.js transfer
unchanged.
Minimal Docker deploy (works on Fly.io, Render, CF Containers):
docker build -t seodesk-mcp .
docker run -p 3333:3333 --env-file .env seodesk-mcpConnect from ChatGPT
ChatGPT → Settings → Apps → Create App (or Connectors).
Server URL:
https://<your-domain>/mcpChatGPT auto-discovers
/.well-known/oauth-protected-resource, registers a client via/oauth/register, and walks the user through OAuth.Once approved, all nine tools appear in ChatGPT and can be invoked in chat.
Connect from Claude / Cursor / Codex
Any MCP client that supports Streamable HTTP + OAuth 2.1 works. Point it at
https://<your-domain>/mcp and it will complete DCR + PKCE the same way.
Production hardening checklist
Replace in-memory
clients/authCodes/refreshTokensstores insrc/oauth.jswith Redis or Postgres.Replace the auto-approve
/oauth/authorizehandler with a real consent page that authenticates the end user against SEODesk (Supabase Auth).Rotate
JWT_SECRETand pinALLOWED_REDIRECT_HOSTS.Put the server behind HTTPS (Railway / Fly / CF terminate TLS for you).
Add rate limiting (e.g.
express-rate-limit) on/mcpand/oauth/*.
This server cannot be deployed
Maintenance
Related MCP Connectors
Open-source AI SEO over MCP: audits, ranks, keywords, backlinks + AI visibility (GEO).
Query, browse, and automate OmegaAI workspaces from any MCP client. Streamable HTTP with OAuth 2.0.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Exposes FEDLIN's public security scanners as agent-callable tools over Streamable HTTP.
Related MCP Servers
AlicenseNot gradedqualityFmaintenanceExposes SEO and AI-readability audit tools to AI agents, enabling one-shot anonymous audits or full authenticated audits with PDF reports and organic traffic data.39 npmMIT- AlicenseAqualityAmaintenanceOAuth-protected Google Search Console MCP for analytics, URL inspection, sitemap management, indexing requests, and SEO diagnostics. Open-source Cloudflare Workers implementation with 17 tools.174,051 npm5MIT

DataForSEO MCP Serverofficial
AlicenseBqualityBmaintenanceModel Context Protocol (MCP) server implementation for DataForSEO, enabling AI assistants to interact with selected DataForSEO APIs and obtain SEO data through a standardized interface.899,164 npmApache 2.0- AlicenseNot gradedqualityCmaintenanceModel Context Protocol server for SignalSumo that lets Claude, Cursor, and other MCP-compatible clients read SEO data, run technical audits, research keywords, and check backlink profiles through natural-language tool calls.6 npmMIT