andyeverything/openproject-mcp-server

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

91 stars 62 forks 质量 65 趋势 15

Repository Install

andyeverything/openproject-mcp-server 是从 https://github.com/andyeverything/openproject-mcp-server. 导入的 MCP 服务器候选

概览

andyeverything/openproject-mcp-server 是从 https://github.com/andyeverything/openproject-mcp-server. 导入的 MCP 服务器候选

概述（AI 翻译）

⚠️ 这是一个早期项目。不要将其用于生产性使用——欢迎贡献！

OpenProject MCP 服务器

一台模型上下文协议（MCP）服务器，提供与 OpenProject API v3 的无缝集成。该服务器使 LLM 应用程序能够与 OpenProject 交互，进行项目管理、工作包跟踪和任务创建。

特色

🔌 完整OpenProject API v3集成
📋 项目管理：列出和筛选项目
📝 工作包管理：创建、列出和筛选工作包
🏷️ 类型管理：列出可用的工作包类型
🔐 安全认证：基于API密钥的认证
🌐 代理支持：可选的HTTP代理配置
🚀 异步操作：采用现代异步/等待模式构建
📊 全面日志：可配置日志层级

先修条件

Python 3.10 或更高版本
uv（快速 Python 包管理器）
OpenProject 实例（云端或自架）
OpenProject API 密钥（由您的用户配置文件生成）

安装

1.安装UV（如果还没安装的话）

macOS/Linux：

Windows：

替代方案（使用pip）:

2.克隆并搭建项目

3.

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

⚠️ This is an early-stage project. Do not use it productively – contributions welcome!

OpenProject MCP Server

A Model Context Protocol (MCP) server that provides seamless integration with OpenProject API v3. This server enables LLM applications to interact with OpenProject for project management, work package tracking, and task creation.

Features

🔌 Full OpenProject API v3 Integration
📋 Project Management: List and filter projects
📝 Work Package Management: Create, list, and filter work packages
🏷️ Type Management: List available work package types
🔐 Secure Authentication: API key-based authentication
🌐 Proxy Support: Optional HTTP proxy configuration
🚀 Async Operations: Built with modern async/await patterns
📊 Comprehensive Logging: Configurable logging levels

Prerequisites

Python 3.10 or higher
uv (fast Python package manager)
An OpenProject instance (cloud or self-hosted)
OpenProject API key (generated from your user profile)

Installation

1. Install uv (if not already installed)

macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows:

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Alternative (using pip):

pip install uv

2. Clone and Setup the Project

git clone https://github.com/yourusername/openproject-mcp.git
cd openproject-mcp

3. Create Virtual Environment and Install Dependencies

# Create virtual environment and install dependencies in one command
uv sync

Alternative (manual steps):

# Create virtual environment
uv venv

# Install dependencies
uv pip install -r requirements.txt

4. Configure Environment

# Copy the environment template
cp env_example.txt .env

Edit .env and add your OpenProject configuration:

OPENPROJECT_URL=https://your-instance.openproject.com
OPENPROJECT_API_KEY=your-api-key-here

Configuration

Environment Variables

Variable	Required	Description	Example
`OPENPROJECT_URL`	Yes	Your OpenProject instance URL	`https://mycompany.openproject.com`
`OPENPROJECT_API_KEY`	Yes	API key from your OpenProject user profile	`8169846b42461e6e...`
`OPENPROJECT_PROXY`	No	HTTP proxy URL if needed	`http://proxy.company.com:8080`
`LOG_LEVEL`	No	Logging level (DEBUG, INFO, WARNING, ERROR)	`INFO`
`TEST_CONNECTION_ON_STARTUP`	No	Test API connection when server starts	`true`

Getting an API Key

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "openproject-fastmcp": {
      "command": "D:\\Promete\\Project\\mcp-openproject\\openproject-mcp-server\\.venv\\Scripts\\python.exe",
      "args": ["D:\\Promete\\Project\\mcp-openproject\\openproject-mcp-server\\openproject-mcp-fastmcp.py"],
      "env": {
        "PYTHONPATH": "D:\\Promete\\Project\\mcp-openproject\\openproject-mcp-server",
        "OPENPROJECT_URL": "https://your-instance.com",
        "OPENPROJECT_API_KEY": "your-api-key"
      }
    }
  }
}