What prerequisites are needed to run OpenProject MCP?
Python 3.10 or higher, `uv` (fast Python package manager), and an OpenProject instance (cloud or self-hosted) with a valid API key generated from the user’s access tokens page.
@AndyEverything
基本信息
A Model Context Protocol (MCP) server that provides seamless integration with OpenProject API v3.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"openproject": {
"command": "/path/to/your/project/.venv/bin/python",
"args": [
"/path/to/your/project/openproject-mcp.py"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
OpenProject MCP is a Model Context Protocol (MCP) server that provides seamless integration with OpenProject API v3, enabling LLM applications (such as Claude Desktop) to perform project management, work package tracking, and task creation. It is intended for developers who want to connect AI assistants to an OpenProject instance (cloud or self-hosted).
Install uv (Python package manager), clone the repository, run uv sync to install dependencies, copy env_example.txt to .env and set OPENPROJECT_URL and OPENPROJECT_API_KEY, then start the server with uv run python openproject-mcp.py. For Claude Desktop, add the server configuration pointing to the Python executable or uv to the claude_desktop_config.json file.
Python 3.10 or higher, `uv` (fast Python package manager), and an OpenProject instance (cloud or self-hosted) with a valid API key generated from the user’s access tokens page.
No, this is an early‑stage project with a WIP status. The README explicitly advises against using it productively and welcomes contributions.
Log in to your OpenProject instance, go to **My account** → **Access tokens**, click **+ Add**, name the token, and copy the generated key.
Yes, set the `OPENPROJECT_URL` environment variable to your self‑hosted instance’s URL. HTTP proxy support is also available via the optional `OPENPROJECT_PROXY` variable.
The server uses the standard MCP transport (stdio for Claude Desktop integration) and authenticates to the OpenProject API v3 via an API key provided in the `.env` file. Connections can optionally go through an HTTP proxy.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
评论