MCP Relay Server
Supported as a deployment platform for hosting the MCP relay server as a long-running HTTP service.
Provides HTTP relay tools for interacting with Supabase REST API, allowing authenticated requests to Supabase resources with configurable path and method restrictions.
Provides HTTP relay tools for interacting with Vercel's API through authenticated requests, enabling management of Vercel resources and deployments.
Click on "Install 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., "@MCP Relay Serverlist my providers"
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.
MCP Relay Server
A lightweight MCP server that exposes provider-specific tools and relays HTTP requests to configured providers (Supabase, Vercel, Context7, etc.).
Quick start
Install dependencies
npm installSet up environment variables
Set environment variables for provider auth tokens (locally or in your host settings):
CONTEXT7_API_KEY=your-token-here
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_ANON_KEY=your-key-hereExample for your shell:
PowerShell:
$env:CONTEXT7_API_KEY = "your-token"Bash:
export CONTEXT7_API_KEY="your-token"
Add a provider
npm run build
node dist/cli.js addRun the relay (stdio transport)
node dist/index.jsRun the relay (HTTP transport)
node dist/httpServer.jsRelated MCP server: Integrations MCP
Provider config
Provider configs live in providers/*.json.
Example:
{
"name": "supabase",
"type": "http",
"baseUrl": "https://YOUR_PROJECT.supabase.co",
"description": "Supabase REST API",
"auth": {
"type": "bearer",
"env": "SUPABASE_TOKEN"
},
"defaultHeaders": {
"apikey": "${SUPABASE_ANON_KEY}"
},
"allowMethods": ["GET", "POST"],
"allowPaths": ["/rest/v1/"]
}Note: set any secrets via environment variables (locally or in your host). ${ENV_VAR} placeholders in baseUrl and defaultHeaders are expanded at runtime.
Presets: providers/vercel.json uses VERCEL_TOKEN. providers/supabase.json uses SUPABASE_URL and SUPABASE_ANON_KEY.
Tools
Each provider creates a tool named:
provider.<name>.request
Inputs:
path: path starting with/method: HTTP methodheaders: additional headersquery: query paramsbody: string or JSON
Optional provider fields:
allowMethods: restricts allowed HTTP methods.allowPaths: list of allowed path prefixes.
The server also exposes:
relay.list_providers
CLI flags
node dist/cli.js add --name supabase --base-url https://xyz.supabase.co --auth bearer --auth-env SUPABASE_TOKENOne-click deploy
Replace YOUR_REPO_URL with your GitHub repo URL.
Vercel (serverless, stateless MCP HTTP at
/mcp):
Render (long-running HTTP server on
/mcp):
Set env vars in your hosting dashboard for any providers you configure (for example VERCEL_TOKEN, CONTEXT7_API_KEY, SUPABASE_URL, SUPABASE_ANON_KEY).
HTTP settings
PORT: port for the HTTP server (default:3000).HOST: bind address for the HTTP server (default:0.0.0.0).MCP_PATH: HTTP path for MCP (default:/mcp).
Build
npm run buildThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Connect MCP clients to 2,000+ AI models without managing provider API keys.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to make HTTP requests (GET, POST, PUT, DELETE) to external APIs through standardized MCP tools.42MIT
- FlicenseNot gradedqualityDmaintenanceA comprehensive MCP server providing over 390 tools across 66 providers, including major SaaS platforms like GitHub, Slack, and Stripe. It enables AI assistants to interact directly with a wide array of public APIs and utility services through a single interface.
- FlicenseNot gradedqualityCmaintenanceA personal MCP connection aggregator that routes tool calls from a single endpoint to multiple backend MCP services like Zo, Context7, Notion, and Canva.
- FlicenseNot gradedqualityCmaintenanceEnables LLM-powered agents to securely communicate with and orchestrate downstream microservices via FastAPI endpoints exposed as MCP tools.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/econ-watch/mcprelay'
If you have feedback or need assistance with the MCP directory API, please join our Discord server