mcpField
A
Awesome Copilot MCP Server

Awesome Copilot MCP Server

Local
github.comAI & Agents4Updated 1d ago
RepositoryVisit website

About Awesome Copilot MCP Server

Awesome Copilot MCP Server indexes agents and other resources from the official github/awesome-copilot repository for MCP clients. It bundles metadata at startup and can refresh it from GitHub during a session.

Key features

  1. 01Index agents, prompts, and instructions
  2. 02Include skills, collections, plugins, hooks, and workflows
  3. 03Search indexed resources
  4. 04Refresh metadata from GitHub
  5. 05Offer HTTP and OpenAPI endpoints

Use cases

  1. 01Find a Copilot agent or prompt
  2. 02Browse skills and workflow resources
  3. 03Search the catalog from an MCP client

MCP support

The MCP server exposes indexed repository content through tools and resources, resolving full content on demand. It supports stdio MCP connections and can also run as an HTTP/OpenAPI server.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "rbbtsn0w-awesome-copilot": {
      "command": "npx",
      "args": [
        "-y",
        "awesome-copilot-mcp"
      ]
    }
  }
}
Run commandnpx -y awesome-copilot-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmawesome-copilot-mcp0.8.7

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Awesome Copilot MCP Server

npm version License: MIT Build Status

A Model Context Protocol (MCP) server that provides access to awesome-copilot agents and collection resources.

Quick Start

One-Click Installation for VS Code

Click the badge to install directly in VS Code (will prompt to open VS Code):

Install in VS Code Install in VS Code Insiders

Note: Requires GitHub Copilot extension in VS Code. Click the badge on GitHub to trigger the installation prompt.

Manual Configuration

Add to your MCP Client configuration (e.g., Claude Desktop or VS Code):

{
  "mcpServers": {
    "awesome-copilot": {
      "command": "npx",
      "args": ["-y", "awesome-copilot-mcp", "start"]
    }
  }
}

This ensures you always run the latest version.

Usage

As MCP Server

Standard stdio usage (default). See configuration above.

As HTTP / OpenAPI Server

Run locally for remote access or OpenAPI testing:

npx -y awesome-copilot-mcp start-http --port 8080 --host 0.0.0.0

Available endpoints:

  • GET /health Health check
  • GET /metadata Return metadata index
  • GET /metadata/stream SSE streaming output of metadata
  • GET /search?q=kw Search
  • GET /openapi.json API Documentation
Supported Content Types

This server now indexes all resources published in the official github/awesome-copilot repository:

  • 🤖 Agents
  • 💬 Prompts
  • 📋 Instructions
  • 🛠️ Skills (folder-aware)
  • 📦 Collections
  • 🎁 Plugins (from plugins/external.json)
  • 🪝 Hooks
  • ⚡ Agentic Workflows

Debugging

MCP Inspector is the recommended way to test and debug:

# Debug via Stdio (Recommended)
npx -y awesome-copilot-mcp debug --no-build

# Debug via HTTP
npm run inspect:http

Architecture

This server uses a Bundled + In-Memory architecture for maximum reliability:

  1. Startup: Loads metadata.json bundled directly within the npm package. Zero external dependencies.
  2. Hot Updates: refresh_metadata fetches the latest data from GitHub and stores it in memory for the current session.
  3. Sandbox Friendly: No local disk cache (~/.cache) is used, preventing permission issues in restricted environments (e.g., macOS App Sandbox).

Environment Variables

VariableDescription
ACP_METADATA_URLOptional. URL to a hosted metadata.json (e.g. https://yourname.github.io/repo/metadata.json). Overrides GitHub raw fetch.
ACP_REPOS_JSONCustom repository configuration JSON.

Metadata Generation

Automated: GitHub Actions runs daily to fetch the latest metadata from github/awesome-copilot and publishes a new npm version if changes are detected.

Internal: The metadata file is lightweight (~170 KB) containing only index info. Actual content and download targets for agents, prompts, instructions, skills, collections, plugins, hooks, and workflows are resolved on-demand via the exposed tools and resources.

Development

# Install dependencies
npm install

# Build
npm run build

# Run tests
npm test

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.