by wojtyniak
Provides a searchable registry of MCP servers, enabling AI assistants to locate and provision tools on demand.
Mcp Mcp offers a “phone‑book” of MCP servers, aggregating over a thousand entries from official lists and community collections. It continuously updates the database every few hours, de‑duplicates sources, and stores pre‑computed embeddings for instant semantic search.
uvx
or pipx
:
uvx mcp-mcp # runs the latest version without a permanent install
# or
pipx install mcp-mcp
uv run main.py
uv run main.py --http --host 0.0.0.0 --port 8000
{
"mcpServers": {
"mcp-mcp": { "command": "uvx", "args": ["mcp-mcp"] }
}
}
justfile
commands (dev, test, build, publish).Q: Do I need an API key to use Mcp Mcp? A: No, the server is open‑source and publicly reachable; only optional environment variables are required for private registries, which are not covered in the core MVP.
Q: Which transport should I choose? A: Use STDIO when integrating with Claude Desktop or other MCP‑compatible clients. Use HTTP for local testing or when you need a REST endpoint.
Q: How often is the server list refreshed? A: Every three hours, pulling the latest changes from the curated sources.
Q: Can I contribute new MCP servers? A: Yes – submit a pull request to the source lists (official or community) and the next automated update will include them.
Q: Is Docker support available? A: Docker integration is planned for a future release (see roadmap).
MCP-MCP is a Meta-MCP Server that acts as a tool discovery and provisioning service for the Model Context Protocol (MCP). When an AI assistant needs a capability that isn't currently available, it can ask MCP-MCP to discover and suggest appropriate MCP servers from a comprehensive database of over a thousand servers aggregated from multiple curated sources.
Think of it as a "phone book" for MCP servers - one tool to find all other tools.
MCP-MCP provides access to a comprehensive database aggregated from multiple curated sources, including:
The database is automatically updated every 3 hours with the latest servers from the community.
Agents Just Wanna Have Tools
Why make agents (and users) hunt for tools when we can bring the tools to them?
Add MCP-MCP to your Claude Desktop configuration file:
~/Library/Application\ Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"mcp-mcp": {
"command": "uvx",
"args": ["mcp-mcp"]
}
}
}
{
"mcpServers": {
"mcp-mcp": {
"command": "mcp-mcp"
}
}
}
Add MCP-MCP to your Claude Code configuration file:
claude mcp add mcp-mcp uvx mcp-mcp
Once configured, you can ask Claude Desktop to discover MCP servers using natural language:
# Clone the repository
git clone https://github.com/your-username/mcp-mcp.git
cd mcp-mcp
# Install dependencies
uv sync
# Run tests
uv run pytest
# Run the server
uv run main.py
For testing the installed package:
uvx mcp-mcp
This installs and runs the MCP-MCP server directly via uvx.
This project includes a justfile
for common development tasks:
# List all available commands
just help
# Development with auto-reload
just dev # STDIO mode with file watching
just dev-http # HTTP mode with file watching
# Running without auto-reload
just run-stdio # STDIO mode
just run-http # HTTP mode
# Testing
just test # Unit tests only
just test-integration # Include GitHub integration tests
# Building and publishing
just build # Build package
just publish-test # Publish to Test PyPI
just publish-prod # Publish to Production PyPI
# Utilities
just version # Show version
just clean # Clean build artifacts
For development and testing, use HTTP transport (easier to stop with Ctrl+C):
# HTTP mode (accessible at http://localhost:8000)
uv run main.py --http
# OR with justfile:
just run-http
# With auto-reload during development
just dev-http
# Custom host/port
uv run main.py --http --host 0.0.0.0 --port 3000
# STDIO mode (for MCP clients like Claude Desktop)
uv run main.py # Note: To stop STDIO mode, use Ctrl+D (EOF), not Ctrl+C
# OR with justfile:
just run-stdio
# With auto-reload during development
just dev
# Build package
uv build
# OR with justfile:
just build
# Test local installation
uvx --from ./dist/mcp_mcp-0.1.0-py3-none-any.whl mcp-mcp
mcp-mcp --help
Option | Description | Default |
---|---|---|
--transport {stdio,http} |
Transport method | stdio |
--http |
Use HTTP transport | - |
--host HOST |
Host for HTTP transport | localhost |
--port PORT |
Port for HTTP transport | 8000 |
# Run all tests (unit + integration)
uv run pytest
# OR with justfile:
just test
# Run only unit tests (fast, no network)
uv run pytest db/ -v
# OR with justfile:
just test-unit
# Run only integration/e2e tests
uv run pytest tests/ -v
# OR with justfile:
just test-integration
# Run GitHub integration tests (optional, requires network)
MCP_MCP_TEST_GITHUB_INTEGRATION=1 uv run pytest tests/
# OR with justfile:
just test-integration-github
# Run all tests including GitHub integration
MCP_MCP_TEST_GITHUB_INTEGRATION=1 uv run pytest
# OR with justfile:
just test-all
# Run with coverage
uv run pytest --cov=db
Test Structure:
db/
alongside the code they test (Go-style)tests/
directoryIntegration Tests: Set MCP_MCP_TEST_GITHUB_INTEGRATION=1
to test real GitHub downloads and verify the complete first-user onboarding experience. These tests ensure users get fast startup (< 5 seconds) with 1,727+ servers.
We welcome contributions! Please see our development setup and:
git checkout -b feature/amazing-feature
)git commit -m 'Add amazing feature'
)git push origin feature/amazing-feature
)This project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ for the MCP ecosystem
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by danny-avila
Provides a customizable ChatGPT‑like web UI that integrates dozens of AI models, agents, code execution, image generation, web search, speech capabilities, and secure multi‑user authentication, all open‑source and ready for self‑hosting.
by ahujasid
BlenderMCP integrates Blender with Claude AI via the Model Context Protocol (MCP), enabling AI-driven 3D scene creation, modeling, and manipulation. This project allows users to control Blender directly through natural language prompts, streamlining the 3D design workflow.
by pydantic
Enables building production‑grade generative AI applications using Pydantic validation, offering a FastAPI‑like developer experience.
by GLips
Figma-Context-MCP is a Model Context Protocol (MCP) server that provides Figma layout information to AI coding agents. It bridges design and development by enabling AI tools to directly access and interpret Figma design data for more accurate and efficient code generation.
by mcp-use
Easily create and interact with MCP servers using custom agents, supporting any LLM with tool calling and offering multi‑server, sandboxed, and streaming capabilities.
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
by lharries
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp that allows users to search, read, and send WhatsApp messages (including media) through AI models like Claude. It connects directly to your personal WhatsApp account via the WhatsApp web multi-device API and stores messages locally in a SQLite database.
by idosal
GitMCP is a free, open-source remote Model Context Protocol (MCP) server that transforms any GitHub project into a documentation hub, enabling AI tools to access up-to-date documentation and code directly from the source to eliminate "code hallucinations."
by Klavis-AI
Klavis AI provides open-source Multi-platform Control Protocol (MCP) integrations and a hosted API for AI applications. It simplifies connecting AI to various third-party services by managing secure MCP servers and authentication.