remote s
Explore a community-maintained list of remote Model Context Protocol (MCP) servers. Find, learn about, and check the reachability of MCP-enabled services.
claude mcp add --transport stdio portal-labs-infrastructure-remote-mcp-servers node path/to/server.js \ --env NEXT_PUBLIC_SUPABASE_URL="YOUR_SUPABASE_PROJECT_URL" \ --env SUPABASE_SERVICE_ROLE_KEY="OPTIONAL_IF_YOU_USE_SERVER_SIDE_PRIVILEGES" \ --env NEXT_PUBLIC_SUPABASE_ANON_KEY="YOUR_SUPABASE_ANON_PUBLIC_KEY"
How to use
Remote MCP Servers provides a dynamic registry of MCP servers that you can discover, filter, and query via a public API. The registry exposes endpoints to fetch approved MCP servers, along with helper endpoints to list all categories and authentication types. You can browse servers by category, search by name or description, and apply filters such as official status, authentication type, and dynamic client registration support. Use the /api/servers endpoint to retrieve a paginated, filterable list, then drill into individual server details for maintainer contact, MCP URL, and metadata. If you’re building an app that consumes MCP servers, this registry acts as a central source of truth for discovery and to feed dynamic client registration or compatibility checks.
How to install
Prerequisites:
- Node.js v18 or later
- npm or yarn
- A Supabase project (for registry data storage and auth)
- Clone the repository:
git clone https://github.com/portal-labs-infrastructure/remote-mcp-servers
cd remote-mcp-servers
- Install dependencies:
npm install
# or
yarn install
- Configure environment variables (production or local development):
- Create a .env.local file in the project root.
- Add your Supabase credentials:
NEXT_PUBLIC_SUPABASE_URL=YOUR_SUPABASE_PROJECT_URL
NEXT_PUBLIC_SUPABASE_ANON_KEY=YOUR_SUPABASE_ANON_PUBLIC_KEY
# Optional: if you use server-side actions with elevated privileges
# SUPABASE_SERVICE_ROLE_KEY=YOUR_SUPABASE_SERVICE_ROLE_KEY
- Start the development server:
npm run dev
# or
yarn dev
The app will typically be available at http://localhost:3000.
Additional notes
Tips:
- The registry uses Supabase for data storage and authentication; ensure your Supabase project has the required tables and RLS configured for your use case.
- If you deploy with production settings, remember to set environment variables in your hosting environment (e.g., Vercel, Netlify, or your own server).
- The API at /api/servers supports filtering by categories, authentication types, search queries, and pagination. Use multiple authTypes or categories by comma-separated values (e.g., authTypes=OAuth,APIKey).
- When submitting new MCP servers, entries may go into a pending review workflow before appearing publicly.
- If you modify the registry schema, update the seed data and any seed scripts accordingly.
Related MCP Servers
MakeMoneyWithAI
A list of open-source AI projects you can use to generate income easily.
drawio2go
A modern DrawIO editor application. AI-Powered, Human-AI Collaboration | AI 加持,人机共绘drawio
ollama -bridge
Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots
hackmd
A Model Context Protocol server for integrating HackMD's note-taking platform with AI assistants.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
architect
A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).