Copilot

Provides an MCP server that enables Copilot-driven chat, explanations, code suggestions, and reviews via MCP-compatible clients.
  • javascript

1

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "willianpaiva-copilot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@willianpaiva/copilot-mcp-server"
      ],
      "env": {
        "DEBUG": "false",
        "LOG_LEVEL": "info",
        "GITHUB_ORG": "YOUR_ORG",
        "MAX_REQUESTS_PER_MINUTE": "60"
      }
    }
  }
}

You can run a Copilot Global MCP Server that integrates with GitHub Copilot to deliver AI-powered code assistance through MCP-compatible clients like Claude Code. It supports chat, code explanations, code generation, and code reviews, using multiple AI models while respecting rate limits and leveraging your existing Copilot authentication.

How to use

Connect to the MCP server from your MCP client and choose from the available tools to interact with Copilot AI models. You can start a local server process or run it via npx, then reference it by its MCP server name in your client configuration. Use copilot_chat for general programming help, copilot_explain for code explanations, copilot_suggest to generate code from descriptions, and copilot_review to receive feedback on your code.

How to install

Prerequisites: you need Node.js and npm installed on your machine.

# Option 1: Run via npx (recommended)
npx -y @willianpaiva/copilot-mcp-server

# Option 2: Manual installation
git clone https://github.com/WillianPaiva/copilot-mcp.git
cd copilot-mcp
npm install
npm run build

# Start the server locally after building (example)
node build/index.js

Post-install steps

No tokens or additional environment setup are required if you already authenticate with GitHub Copilot on your system. The server automatically uses your existing Copilot authentication.

Optional configuration is supported by creating a .env file to override defaults. The following variables are shown for reference:

# Optional: override detected organization
GITHUB_ORG=your_organization_name

# Optional debugging controls
LOG_LEVEL=info
DEBUG=false
MAX_REQUESTS_PER_MINUTE=60

Available tools

copilot_chat

Interact with Copilot to get general programming assistance, ask questions, and receive AI-powered help tailored to your context.

copilot_explain

Provide detailed explanations of code snippets to help you understand how they work and why they behave as they do.

copilot_suggest

Generate code based on natural language prompts, supporting rapid prototyping and code generation.

copilot_review

Receive code reviews and improvement suggestions, including security and style recommendations.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational