radicle-mcp
MCP Server for radicle.xyz decentralized git-based PR and issues
Documentation
Radicle + GitHub MCP Server
A Model Context Protocol (MCP) server setup that provides tools for interacting with both Radicle (peer-to-peer code collaboration) and GitHub through a unified interface.
Features
This setup includes two MCP servers:
๐ Radicle MCP Server (Python)
- Repository Management: Initialize, clone, and inspect Radicle repositories
- Synchronization: Sync repositories with the Radicle network
- Patches & Issues: List and manage patches and issues
- Node Information: Get node ID and remote information
- Help System: Access Radicle command documentation
- ๐ GitHub Integration: Bidirectional sync of issues and PRs between GitHub and Radicle
๐ GitHub MCP Server (Official)
- Repository Operations: Create, fork, clone GitHub repositories
- Issue Management: Create, update, and manage GitHub issues
- Pull Requests: Manage pull requests and reviews
- File Operations: Read, write, and manage repository files
- Search: Search repositories, issues, and code
- User Management: Manage user and organization information
๐ GitHub โ Radicle Synchronization
- Bidirectional Issue Sync: Automatically sync issues between platforms
- Idempotent Operations: Safe to run multiple times without duplicates
- Metadata Preservation: Maintains original author, links, and timestamps
- Mapping Database: Tracks relationships between GitHub and Radicle items
- MCP Integration: Available as AI assistant tools
Available Tools
Repository Operations
- `rad_init`: Initialize a new Radicle repository
- `rad_clone`: Clone an existing repository by RID
- `rad_status`: Get repository status and information
- `rad_sync`: Sync repository with the network
- `rad_push`: Push changes to the network
Collaboration Features
- `rad_patch_list`: List patches (pull requests) in a repository
- `rad_issue_list`: List issues in a repository
- `rad_remote_list`: List remotes/nodes for a repository
Node & Identity
- `rad_id`: Get your Radicle node ID
- `rad_help`: Get help for Radicle commands
Prerequisites
1. Radicle CLI: Ensure the `rad` command is installed and available in your PATH
# Install Radicle (see https://radicle.xyz for installation instructions)
curl -sSf https://install.radicle.xyz | sh2. Deno: For running the GitHub MCP server
# Install Deno
curl -fsSL https://deno.land/install.sh | sh3. Python Environment: Python 3.8+ with the MCP library
pip install mcp4. GitHub Personal Access Token: For GitHub integration
Installation
1. Clone this repository
2. Install dependencies:
pip install -e .3. Install the official GitHub MCP server:
deno install -g --name github-mcp npm:@modelcontextprotocol/server-github4. Run the setup script:
python setup_mcp.pyUsage
Quick Setup
# Set your GitHub token
export GITHUB_PERSONAL_ACCESS_TOKEN=your_token_here
# Run the setup script
python setup_mcp.pyGitHub โ Radicle Sync
# Test sync connectivity
python demo_sync.py
# Create a test issue (optional)
python create_test_issue.py
# Run full sync
python github_radicle_sync.py
# Or use CLI interface
python sync_cli.py --repo owner/repo --dry-run
python sync_cli.py --repo owner/repo --issues-onlyMCP Integration
The sync functionality is available as MCP tools:
- `github_sync_test`: Test connectivity
- `github_sync_issues`: Sync issues only
- `github_sync_full`: Full bidirectional sync
See SYNC_README.md for detailed sync documentation.
As Standalone Servers
# Radicle MCP Server
python -m radicle_mcp.server
# GitHub MCP Server
github-mcpWith Claude Desktop
The setup script automatically creates the configuration. Your `claude_desktop_config.json` will include:
{
"mcpServers": {
"radicle-mcp": {
"command": "/path/to/python",
"args": ["-m", "radicle_mcp.server"]
},
"github-mcp": {
"command": "/path/to/github-mcp",
"args": [],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_PERSONAL_ACCESS_TOKEN}"
}
}
}
}VS Code Integration
This project includes VS Code configuration for debugging the MCP server. Use the provided `mcp.json` file to connect compatible MCP clients.
Example Commands
Once connected to an MCP client, you can use natural language to interact with both platforms:
Radicle Operations
- "Initialize a new Radicle repository called 'my-project'"
- "Clone the repository with RID rad:z2..."
- "Show me the current patches in this repository"
- "Sync this repository with the network"
- "What's my Radicle node ID?"
GitHub Operations
- "Create a new GitHub repository called 'awesome-project'"
- "List my recent GitHub repositories"
- "Create an issue titled 'Bug fix needed'"
- "Show me open pull requests in my repository"
- "Search for repositories related to 'machine learning'"
Cross-Platform Workflows
- "Publish this Radicle repository to GitHub"
- "Sync issues between Radicle and GitHub"
- "Compare this repository on both platforms"
Development
Running Tests
python -m pytest tests/Code Style
black src/
flake8 src/Project Structure
radicle-mcp/
โโโ src/radicle_mcp/
โ โโโ __init__.py
โ โโโ server.py # Main MCP server implementation
โโโ .vscode/
โ โโโ mcp.json # VS Code MCP configuration
โโโ .github/
โ โโโ copilot-instructions.md
โโโ pyproject.toml # Project configuration
โโโ README.mdContributing
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request
License
MIT License - see LICENSE file for details
Related Links
Frequently asked questions
What is radicle-mcp?
radicle-mcp is MCP Server for radicle.xyz decentralized git-based PR and issues
How do I install radicle-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is radicle-mcp open source?
Yes โ it is hosted on GitHub at https://github.com/fovi-llc/radicle-mcp.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP