
MCP Manager
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.
README
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
# Clone the repository
git clone <your-repo-url>
cd <your-repo-directory>
# Install dependencies
npm install
# Create a .env file from the example
cp .env.example .env
# Edit .env to configure your MCP Manager
nano .env
Running the Server
# Run in development mode
npm run dev
# Build and run in production mode
npm run build
npm run start
Configuration Options
Configure your MCP Manager by editing the .env
file:
# Server Configuration
PORT=5000 # Main server port
HOST=0.0.0.0 # Host to bind to
NODE_ENV=development # Environment (development/production)
REUSE_PORT=true # Whether to reuse the port
# MCP Port Range
MCP_PORT_RANGE_START=50050 # Start port for MCP servers
MCP_PORT_RANGE_END=50150 # End port for MCP servers
# MCP Compatibility Settings
MCP_WORKER_MODE=false # Enable worker mode
MCP_DISCOVERY_ENABLED=true # Enable auto-discovery of MCP servers
MCP_AUTOSTART_SERVERS=true # Automatically start MCP servers
# Smithery API Configuration
SMITHERY_API_KEY=your_smithery_api_key_here # API key for Smithery packages
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:
GET /?api_key=YOUR_API_KEY&headless=true&auto_connect=true
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:
ws://localhost:5000/ws
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.