Github Chat MCP

Feedback

What features would you love to see? | どんな機能が欲しいですか？ | Join our Discord to share ideas!

Suggest

Use GitHub Chat with Cursor, Claude, and other MCP-compatible assistants to understand codebases instantly.

Get Started with MCP

Explore Now

Model Context Protocol (MCP) Support

Use GitHub Chat directly with Cursor, Claude, and other AI coding assistants.

Quick Installation

# Install with pip
pip install github-chat-mcp

# Or with uv
brew install uv
uv install github-chat-mcp

Cursor Setup

{
"mcpServers": {
  "github-chat": {
    "command": "uvx",
    "args": ["github-chat-mcp"]
  }
}
}

💡

After setup, simply ask your AI Assistant: “Ask GitHub Chat how to integrate with the supabase: https://github.com/AsyncFuncAI/github-chat-mcp”

Try It Now For Free

Repository Indexing

Index any public GitHub repository for analysis

AI Chat API

Ask questions about any indexed repository via API

Developer-First

Simple one-liner API to start immediately

GitHub Chat API

GitHub Chat API gives you programmatic access to chat with any public GitHub repository. Just two simple endpoints to integrate AI-powered code understanding into your workflow.

Repository Indexing

First, index a GitHub repository to analyze its codebase.

POST https://api.github-chat.com/verify

1curl -X POST https://api.github-chat.com/verify \
2  -H "Content-Type: application/json" \
3  -d '{"repo_url": "https://github.com/hacksider/Deep-Live-Cam"}'

This endpoint processes the repository and makes it available for chat interactions.

Chat with Repository

Ask questions about the repository and receive detailed AI responses.

POST https://api.github-chat.com/chat/completions/sync

1curl -X POST https://api.github-chat.com/chat/completions/sync \
2  -H "Content-Type: application/json" \
3  -d '{
4    "repo_url": "https://github.com/hacksider/Deep-Live-Cam",
5    "messages": [{"role": "user", "content": "What is the core tech stack?"}]
6  }'

The messages array can contain conversation history for multi-turn conversations.

3. Response Format

Responses from the API include detailed information structured in a way that separates the reasoning, answer, and source context.

Rationale

The AI's explanation of how it approached the question, showing its reasoning process.

Answer

The formatted answer to the query, with Markdown support for rich text formatting.

Contexts

Repository content used by the AI to generate the response, with metadata about each file.

API Response Example (Click to expand)

1{
2  "rationale": "The user is asking about the backend technologies used in the Deep-Live-Cam project. I need to look through the files to identify the programming languages, libraries, and frameworks used for the backend functionality.",
3  "answer": "The Deep-Live-Cam project uses the following backend technologies:\n\n*   **Python**: The core logic and scripting are written in Python.\n*   **PyTorch**: Used for tensor computations and GPU acceleration.\n*   **ONNX Runtime**: Provides cross-platform machine learning model execution.\n*   **TensorFlow**: Used for machine learning tasks.\n*   **gfpgan**:  Used for face enhancement.\n*   **ffmpeg**: Used for video-related operations.",
4  "contexts": [
5    {
6      "text": "<h1 align=\"center\">Deep-Live-Cam</h1>\n\n<p align=\"center\">\n  Real-time face swap and video deepfake with a single click and only a single image.\n</p>\n\n<p align=\"center\">\n  <img src=\"media/demo.gif\" alt=\"Demo GIF\" width=\"800\">\n</p>",
7      "meta_data": {
8        "file_path": "README.md",
9        "type": "md",
10        "is_code": false,
11        "is_implementation": false,
12        "title": "README.md",
13        "token_count": 3790
14      }
15    },
16    // Additional contexts truncated for brevity
17  ]
18}

GitHub Chat vs GitHub Copilot

While both tools help developers understand code, they serve different purposes and complement each other.

Feature	GitHub Chat	GitHub Copilot
Purpose	Repository-wide code understanding	File-based coding assistance
Knowledge Source	Full repository analysis (500MB limit)	Limited open file context
Primary Use	Explore & understand existing codebases	Generate & complete new code
API Access	✅ Simple REST API	❌ No public API