tangaratta-engineering/openproject-mcp-server

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

15 stars 11 forks 品質 65 トレンド 25

Repository Install

A FastMCP-powered server that enables AI assistants like Claude to interact with OpenProject installations.

概要

A Model Context Protocol (MCP) server that enables AI assistants to interact with OpenProject installations. Create projects, manage work packages, assign team members, and generate Gantt charts through natural language commands. - : Create and manage OpenProject projects - : Create, update, and assign work packages with dates - : Create relationships between work packages for Gantt charts - : Find and assign users by email address - : Manage project members and their roles - : Automatically loads work package types, statuses, and priorities - : Project status reports and team workload analysis - OpenProject instance (local or cloud) - API key from your OpenProject profile - Python 3.8+ or Docker Create a .env file with your OpenProject details: 1. Login to your OpenProject instance 2. Go to → 3. Click 4. Enter a name (e.g., "MCP Server") 5.

README

以下は原文 README の抜粋です。原文を見る。

OpenProject MCP Server

Features

Project Management: Create and manage OpenProject projects
Work Package Operations: Create, update, and assign work packages with dates
Dependency Management: Create relationships between work packages for Gantt charts
User Management: Find and assign users by email address
Team Collaboration: Manage project members and their roles
Dynamic Configuration: Automatically loads work package types, statuses, and priorities
Comprehensive Reporting: Project status reports and team workload analysis

Installation

Prerequisites

OpenProject instance (local or cloud)
API key from your OpenProject profile
Python 3.8+ or Docker

Method 1: Docker (Recommended)

Clone the repository:
```
git clone 
cd openproject-mcp-server
```

Configure environment:

cp env.example .env
# Edit .env with your OpenProject details

Deploy with Docker:
```
./scripts/deploy.sh deploy 39127
```

Method 2: Python

Clone and setup:

git clone 
cd openproject-mcp-server
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

Configure environment:

cp env.example .env
# Edit .env with your OpenProject details

Test configuration:
```
python3 scripts/test_mvp.py
```

Configuration

Create a .env file with your OpenProject details:

# OpenProject Instance URL (include protocol)
OPENPROJECT_URL=http://localhost:8080

# OpenProject API Key (from your user profile)
OPENPROJECT_API_KEY=your_40_character_api_key_here

# MCP Server Configuration (optional)
MCP_HOST=localhost
MCP_PORT=39127
MCP_LOG_LEVEL=INFO

Getting your OpenProject API Key

Login to your OpenProject instance
Go to My Account → Access Tokens
Click + New token
Enter a name (e.g., “MCP Server”)
Copy the generated 40-character token

Usage

Starting the Server

Docker:

./scripts/deploy.sh deploy 39127

Python:

python3 scripts/run_server.py

MCP Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

For Docker deployment:

{
  "mcpServers": {
    "openproject": {
      "transport": "sse",
      "url": "http://localhost:39127/sse"
    }
  }
}

For local Python:

{
  "mcpServers": {
    "openproject": {
      "command": "python3",
      "args": ["/full/path/to/openproject-mcp-server/scripts/run_server.py"],
      "env": {
        "OPENPROJECT_URL": "http://localhost:8080",

GitHub で README 全文を見る

インストール

docker run -d \

MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "openproject": {
      "transport": "sse",
      "url": "http://localhost:39127/sse"
    }
  }
}