phabricator-mcp-server
Language:
Python
Stars:
5
Forks:
1
README
Phabricator MCP Server
A Model Context Protocol (MCP) server implementation for interacting with Phabricator API. This server allows LLMs to interact with Phabricator through a standardized interface.
Overview
This project provides an MCP server that exposes Phabricator functionality through:
- Task management (viewing, creating, updating tasks)
- Project information
- User details
Getting Started
Prerequisites
- Python 3.8+
- Phabricator API token (from your Phabricator instance)
- Access to a Phabricator instance
Installation
-
Clone this repository:
git clone https://github.com/baba786/phabricator-mcp-server.git cd phabricator-mcp-server -
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Unix/MacOS # or .\venv\Scripts\activate # On Windows -
Install dependencies:
pip install -r requirements.txt -
Set up your environment:
# Copy the example env file cp .env.example .env
Edit .env and add your Phabricator token
Replace 'your-token-here' with your actual Phabricator API token
echo "PHABRICATOR_TOKEN=your-token-here" > .env
5. Run the server:
```bash
cd src
python server.py
Usage
Currently supported commands:
get-task: Retrieve details of a specific Phabricator task
Example usage through the client:
from src.mcp_minimal_client import Client
client = Client()
response = client.get_task(task_id="123") # Replace with actual task ID
print(response)
Development Status
🚧 This project is currently under development. Stay tuned for updates!
Publisher info
More MCP servers built with Python
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.