Integrations
Uses .env files for configuration management, allowing users to customize server settings, MCP compatibility options, and API connections.
Used for cloning the repository during installation, enabling users to obtain the source code.
Automatically discovers MCP servers on GitHub as part of its auto-discovery feature, enabling users to find and use tools from GitHub repositories.
MCP Manager
A flexible Model Context Protocol (MCP) manager server that enables communication between AI models and tools. Compatible with Claude, MCP Dockmaster, and other MCP clients.
Features
- MCP Server Management: Run multiple MCP servers and manage them from a single interface
- Worker Mode: Operate as a worker for other MCP clients
- Auto-Discovery: Automatically find MCP servers on GitHub and from Smithery packages
- Tool Registry: Browse and install tools from a registry of MCP tools
- WebSocket Communication: JSON-RPC over WebSockets for real-time communication
- Headless Mode: Run in headless mode for API-first operation
Getting Started
Prerequisites
- Node.js (v18+)
- NPM (v8+)
Installation
Running the Server
Configuration Options
Configure your MCP Manager by editing the .env
file:
Using MCP Manager with Claude and Other MCP Clients
MCP Manager is designed to be compatible with various MCP clients, including:
- Claude Desktop
- MCP Dockmaster
- Toolbase
- Other MCP compatible clients
Connecting to Claude Desktop
- Run MCP Manager on your local machine
- Open Claude Desktop
- Go to Settings > Advanced > MCP Configuration
- Set the MCP Server URL to
http://localhost:5000/ws
- MCP Manager will appear as an available server in Claude
Connecting to MCP Dockmaster
- Run MCP Manager on your local machine
- Open MCP Dockmaster
- Click "Add Server"
- Enter the server information:
- Name: MCP Manager
- Address: localhost
- Port: 5000
- Click "Connect"
Using Worker Mode
MCP Manager can operate as a worker for other MCP clients:
- Set
MCP_WORKER_MODE=true
in your.env
file - Run MCP Manager
- Connect to MCP Manager from your MCP client
- MCP Manager will automatically discover and register available tools
Headless/API-First Operation
MCP Manager supports headless operation for API-first clients:
Query parameters:
api_key
: Your API key (if required)headless
: Enable headless modeauto_connect
: Automatically connect to available MCP serversws_url
: Specify a custom WebSocket URLserver_id
: Connect to a specific server ID
API Reference
MCP Manager implements the JSON-RPC protocol over WebSockets. The main API endpoint is:
Available Methods
ping
: Test server connectivitygetServers
: Get all registered serversgetServer
: Get server by IDtoggleWorker
: Toggle worker status for a servergetTools
: Get all toolsgetToolsByServer
: Get tools for a specific serveractivateTool
: Activate a tooldeactivateTool
: Deactivate a toolgetStats
: Get server statistics
License
MIT
This server cannot be installed
A flexible server that enables communication between AI models and tools, supporting multiple MCP servers and compatible with Claude, MCP Dockmaster, and other MCP clients.