MCP Server Copilot
A meta MCP server that scales LLMs to 1000+ servers via automatic routing, without exposing all servers and tools directly.
README
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.
<p align="center"> <img src="https://github.com/user-attachments/assets/7bb3ac79-6706-4fc5-8dab-2f0a3e5b981c" alt="mcp_copilot" style="max-width:100%; height:auto; width:500px;"> </p>
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:
<details> <summary>Using uvx</summary>
{
"mcpServers": {
"copilot": {
"command": "uvx",
"args": ["mcp-server-copilot", "--config", "~/.config/mcp-server-copilot/config.json"]
}
}
}
</details>
<details> <summary>Using pip installation</summary>
{
"mcpServers": {
"copilot": {
"command": "python",
"args": ["-m", "mcp_server_copilot", "--config", "~/.config/mcp-server-copilot/config.json"]
}
}
}
</details>
TODOs
- [ ] Add Dockerfile
- [ ] Tune prompt and add show cases
- [ ] Manage Servers more easily
- [ ] Add Semantic Routing
- [ ] Add Planning Capabilities
- [ ] Resources & Prompts
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.