MCP Server Copilot

A meta Model Context Protocol (MCP) server that seamlessly scales LLMs to 1000+ MCP servers through automatic routing without expose all servers and tools to LLMs directly.

Components

Tools

• router-servers: Route user query to appropriate MCP servers.

  • query (string, required): User's query to find relevant servers.
  • top_k (integer, optional): Maximum number of servers to return (default: 5).

• route-tools: Route user query to appropriate MCP tools across all servers.

  • query (string, required): User's query to find relevant tools.
  • top_k (integer, optional): Maximum number of tools to return (default: 5).

• execute-tool: Execute a specific tool on a specific server based on previous routing results.

  • server_name (string, required): Name of the server hosting the tool.
  • tool_name (string, required): Name of the tool to execute.
  • params (object, optional): Parameters to pass to the tool, as a key-value dictionary (default: null or empty object).

Installation

Using uv (recommended)

When using uv no specific installation is needed. We will use uvx to directly run mcp-server-copilot.

Using PIP

Alternatively you can install mcp-server-copilot via pip:

pip install mcp-server-copilot

After installation, you can run it as a script using:

python -m mcp_server_copilot

Configuration

Copy config/config.sample.json to ~/.config/mcp-server-copilot

Add to your MCP Client settings:

"mcpServers": {
  "copilot": {
    "command": "uvx",
    "args": ["mcp-server-copilot", "--config", "~/.config/mcp-server-copilot/config.json"]
  }
}

"mcpServers": {
  "copilot": {
    "command": "python",
    "args": ["-m", "mcp_server_copilot", "--config", "~/.config/mcp-server-copilot/config.json"]
  }
}

TODOs

• Manage Servers more easily
• Add Semantic Routing
• Add Planning Capabilities