A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
A unified gateway for Model Context Protocol (MCP) servers that lets you discover, configure, and access MCP tools from
A unified gateway for Model Context Protocol (MCP) servers that enables discovery, configuration, and access to tools from GitHub repositories through a single endpoint.
https://github.com/user-attachments/assets/f011f8bf-6c99-4a8a-8236-f8eb0a3fb9e4
Current Version: 0.8.0
Note: This project is in beta. APIs and features are subject to change.
MCP Anywhere provides:
📚 Full documentation is available at mcpanywhere.com
# Clone repository
git clone https://github.com/locomotive-agency/mcp-anywhere.git
cd mcp-anywhere
# Install with uv (recommended)
uv sync
# Or install with pip
pip install -e .
# Configure environment
cp env.example .env
# Edit .env with required values:
# SECRET_KEY=<secure-random-key>
# ANTHROPIC_API_KEY=<your-api-key>
# Start server
mcp-anywhere serve http
# Or: python -m mcp_anywhere serve http
# Access at http://localhost:8000
# Install Fly CLI
curl -L https://fly.io/install.sh | sh
# Deploy application
cd mcp-anywhere
fly launch
fly secrets set SECRET_KEY=<secure-random-key>
fly secrets set JWT_SECRET_KEY=<jwt-secret-key>
fly secrets set ANTHROPIC_API_KEY=<your-api-key>
fly secrets set GOOGLE_OAUTH_CLIENT_ID=<google-oauth-client-id>
fly secrets set GOOGLE_OAUTH_CLIENT_SECRET=<google-oauth-client-secret>
fly deploy
# Application available at https://your-app.fly.dev
To speed up the fly.io deployment, you can configure manual build and start of containers.
# set the environment variable
REBUILD_CONTAINERS_ON_STARTUP=false
Deploying the application as a docker container using docker compose.
# Configure environment
cp env.example .env
# Edit .env with required values:
# SECRET_KEY=<secure-random-key>
# ANTHROPIC_API_KEY=<your-api-key>
Build and Deploy the application
$ docker compose -f docker-compose.native.yml up -d --build
View logs to see status
$ docker logs mcp-anywhere-app
Navigate to http://<DOCKER-HOST>:8000/ to use the application
Interact with the machine via CLI, useful for interacting with the database using sqlite3
# fetch machine id for your app
$ fly --app mcp-anywhere-app machine list
$ fly console --app mcp-anywhere-app --machine <MACHINE_ID>
Sample database commands, once logged in to the machine console
$ sqlite3 /.data/mcp_anywhere.db ".tables"
$ sqlite3 /.data/mcp_anywhere.db "SELECT * FROM users;"
Use the web interface to add MCP server repositories:
https://github.com/modelcontextprotocol/servershttps://github.com/yzfly/mcp-python-interpreterThe system uses Claude AI to automatically analyze and configure repositories.
MCP Anywhere supports secure upload and management of credential files for MCP servers:
Supported File Types:
Features:
Usage via Web Interface:
GOOGLE_APPLICATION_CREDENTIALS)Security Considerations:
DATA_DIR/secrets/<server_id>/Claude Desktop Configuration:
First run which uv, which will print out a path to the uv binary. For example on macOS:
/Users/yourname/.local/bin/uv
You can then use that in the start command. Change the --directory path to your MCP Anywhere clone path.
{
"mcpServers": {
"mcp-anywhere": {
"command": "/Users/yourname/.local/bin/uv",
"args": ["run", "--directory", "/Users/yourname/Projects/mcp-anywhere", "mcp-anywhere", "connect"]
}
}
}
Lastly, set up the MCP Anywhere application before starting Claude Desktop:
uv run mcp-anywhere serve stdio
Authentication Options:
For Google OAuth (recommended for teams):
GOOGLE_OAUTH_CLIENT_ID=your-client-id
GOOGLE_OAUTH_CLIENT_SECRET=your-client-secret
GOOGLE_OAUTH_REDIRECT_URI=/auth/callback
OAUTH_USER_ALLOWED_DOMAIN=company.com # Optional: restrict to your domain
/auth/loginHTTP API Integration:
from fastmcp import Client
from fastmcp.client.auth import BearerAuth
async with Client(
"https://your-app.fly.dev/mcp/",
auth=BearerAuth(token="<oauth-token>")
) as client:
tools = await client.list_tools()
Command Line Interface:
# For MCP client connection
mcp-anywhere connect
# Or: python -m mcp_anywhere connect
# For STDIO server mode (local Claude Desktop integration)
mcp-anywhere serve stdio
# For HTTP server mode with OAuth (production)
mcp-anywhere serve http --host 0.0.0.0 --port 8000
Client Application → MCP Anywhere Gateway → Docker Containers → MCP Tools
↓
Web Management Interface
Areas for contribution:
SECRET_KEY # Session encryption key
ANTHROPIC_API_KEY # Claude API key for repository analysis
JWT_SECRET_KEY # JWT token signing key (defaults to SECRET_KEY)
WEB_PORT # Web interface port (default: 8000)
DATA_DIR # Data storage directory (default: .data)
DOCKER_TIMEOUT # Container operation timeout in seconds (default: 300)
LOG_LEVEL # Logging level (default: INFO)
GITHUB_TOKEN # GitHub token for private repository access
# Container Management
CLEANUP_CONTAINERS_ON_SHUTDOWN # Clean up containers on app shutdown (default: false)
REBUILD_CONTAINERS_ON_STARTUP # Rebuild containers on startup (default: true)
# Google OAuth (optional - enables Google authentication)
GOOGLE_OAUTH_CLIENT_ID # Google OAuth client ID
GOOGLE_OAUTH_CLIENT_SECRET # Google OAuth client secret
GOOGLE_OAUTH_REDIRECT_URI # OAuth redirect URI (e.g., /auth/callback)
OAUTH_USER_ALLOWED_DOMAIN # Restrict access to specific domain (e.g., company.com)
# Install development dependencies
uv sync --group dev
# Run tests
uv run pytest
# Run linting
uv run ruff check src/ tests/
# Run type checking
uv run mypy src/
# Run all tests
uv run pytest
# Run tests with coverage
uv run pytest --cov=mcp_anywhere
uv run mcp-anywhere serve http --host 0.0.0.0 --port 8080
LOG_LEVEL=DEBUG mcp-anywhere serve http
mcp-anywhere reset --confirm
See LICENSE
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots
MCP server integration for DaVinci Resolve Studio
A Jetbrains IDE IntelliJ plugin aimed to provide coding agents the ability to leverage intelliJ's indexing of the codeba