mcpField
G
GitHub Repository Assistant

GitHub Repository Assistant

Local
github.com/deploypilotorgVersion Control0Updated 79w ago
Repository

About GitHub Repository Assistant

GitHub Repository Assistant lets Claude inspect public GitHub repositories and help with code-related tasks through a Streamlit interface. It combines repository cloning and analysis with specialized MCP tools.

Key features

  1. 01Clone and analyze public repositories
  2. 02Read repository files
  3. 03Ask Claude questions about code
  4. 04Generate deployment files and workflows
  5. 05Streamlit interface

Use cases

  1. 01Inspect a repository's structure and source files
  2. 02Request a GitHub Actions deployment workflow
  3. 03Generate a Dockerfile for an application

MCP support

The MCP server provides tools to clone, analyze, and read GitHub repositories. The Streamlit frontend connects to the server so Claude can use those tools.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

GitHub Repository Assistant

A tool that uses the MCP (Model Control Protocol) to connect Claude with GitHub repositories, allowing users to analyze code and get assistance with tasks like creating deployment workflows.

Features

  • Clone and analyze any GitHub repository
  • Interact with repositories through Claude 3.5 Sonnet
  • Request deployment workflows and other code generation tasks
  • Seamless integration via Streamlit frontend
  • MCP server with specialized tools for repository interaction

Requirements

  • Python 3.13 or higher
  • Git installed and available in PATH
  • An Anthropic API key

Installation

  1. Clone this repository:

    git clone <your-repo-url>
cd <repo-directory>

  2. Install the required dependencies:

    pip install -r requirements.txt

  3. Set your Anthropic API key in the .env file:

    ANTHROPIC_API_KEY=your_api_key_here

Usage

  1. Start the Streamlit application:

    streamlit run app.py

  2. In the sidebar, connect to the MCP server by entering the path to the server.py file in the "Server Script Path" field and clicking "Connect to Server".

  3. Enter a GitHub repository URL (e.g., https://github.com/deploypilotorg/example-repo) and click "Analyze Repository".

  4. Once the repository is analyzed, you can interact with it by asking questions or requesting tasks like:

    • "What files are in this repository?"
    • "What does the main.py file do?"
    • "Create a GitHub Actions workflow for deploying this code"
    • "Generate a Dockerfile for this application"

How It Works

The application uses the Model Control Protocol (MCP) to enable Claude to interact with GitHub repositories through specialized tools:

  1. The MCP server (server.py) provides tools for cloning, analyzing, and reading from GitHub repositories
  2. The Streamlit frontend (app.py) provides a user-friendly interface for interactions
  3. Claude uses the provided tools to understand repository structure and generate relevant responses

Limitations

  • Currently only supports public GitHub repositories
  • Large repositories may take longer to clone and analyze
  • Generated deployment workflows may need manual adjustments based on specific requirements

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.