baba786

Phabricator MCP Server

Community baba786
Updated

A Model Context Protocol (MCP) server for interacting with Phabricator API

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

  1. Clone this repository:
git clone https://github.com/baba786/phabricator-mcp-server.git
cd phabricator-mcp-server
  1. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Unix/MacOS
# or
.\venv\Scripts\activate  # On Windows
  1. Install dependencies:
pip install -r requirements.txt
  1. 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
  1. Run the server:
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

๐Ÿšง This project is currently under development. Stay tuned for updates!

MCP Server ยท Populars

MCP Server ยท New

    LeulAria

    Aria Icons

    MCP server for 340k SVG icons

    Community LeulAria
    knowall-ai

    Reverie โ€” graph memory that dreams

    Memory management MCP server for AI agents using Neo4j knowledge graphs

    Community knowall-ai
    keploy

    Key Highlights

    Open-source platform for creating safe, isolated production sandboxes for API, integration, and E2E testing.

    Community keploy
    hermes-labs-ai

    Fidelis Memory

    Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. MIT.

    Community hermes-labs-ai
    n24q02m

    Better Code Review Graph

    Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

    Community n24q02m