Github Agentic Chat

🚀 GitHub Productivity Chat MCP Server

This is a Model Context Protocol (MCP) server implemented for GitHub productivity chat, written in the Go programming language. It provides tools to interact with GitHub through natural language and includes vector search capabilities.

🚀 Quick Start

This MCP server allows users to interact with GitHub using natural language and perform vector searches. Follow the steps below to get started.

✨ Features

• Search GitHub repositories.
• Create issues.
• Vector search capabilities:
  • Add documents to the vector repository.
  • Conduct semantic searches in the stored documents.
• An extensible structure for easy addition of more features.

📦 Installation

Prerequisites

• Go 1.21 or higher.
• PostgreSQL database with the pgvector extension installed.
• GitHub personal access token.
• OpenAI API key.
• Claude Desktop or other MCP-compatible clients.

Steps

1. Clone the repository:

git clone https://github.com/akhidasTech/github-agentic-chat-mcp.git
cd github-agentic-chat-mcp

2. Set environment variables:

export GITHUB_TOKEN=your_github_token_here
export DATABASE_URL=postgres://username:password@localhost:5432/database_name
export OPENAI_API_KEY=your_openai_api_key_here

3. Install the pgvector extension in PostgreSQL:

CREATE EXTENSION vector;

4. Build the server:

go build -o bin/github-agentic-chat-mcp

5. Configure Claude Desktop: Edit the ~/Library/Application Support/Claude/claude_desktop_config.json file:

{
    "mcpServers": {
        "github-chat": {
            "command": "/absolute_path/bin/github-agentic-chat-mcp"
        }
    }
}

6. Restart Claude Desktop.

💻 Usage Examples

Available Tools

GitHub Tools

Search Repositories

Search GitHub repositories using a query string.

Create Issues

Create new issues in a specified GitHub repository.

Vector Search Tools

Add to Vector Repository

Add documents to the vector repository to support semantic searches.

Parameters:

• content: The text content to be stored.
• metadata: A JSON string containing content metadata.

Example:

{
    "content": "This is documentation about GitHub Actions",
    "metadata": "{\"type\": \"documentation\", \"tags\": [\"github\", \"ci-cd\"]}"
}

Vector Search

Perform a semantic search in the stored documents.

Parameters:

• query: The search query text.
• limit: The maximum number of results to return (default is 5).

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License.