OpenProject CE MCP
An MCP server for OpenProject that lets local AI agents read and manage project data through structured, guarded tools.
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
An MCP server for OpenProject that lets local AI agents read and manage project data through structured, guarded tools.
MCP server for OpenProject Community Edition: projects, work packages, time tracking, meetings, wiki and more as preview-first tools for AI agents such as Claude Code, Codex and GitHub Copilot.
The server runs as a local subprocess of your MCP client over stdio. It wraps OpenProject API v3 and exposes typed tools for projects, work packages, memberships, versions, boards, time entries, and more.
Reading this on PyPI? All links below point to the GitHub repository — the
docs/pages and images ship in the git repo and source distribution, not in the installed package itself.
select; see Context efficiency for the full numbers.Projects
Work packages
Boards and views
Users and groups
Supporting data
All write operations follow a preview-then-confirm pattern: call a tool once to get a validated preview, then again with confirm=true to execute. There is no way to bypass this.
This MCP server targets OpenProject Community Edition only. It does not support Enterprise Edition features such as:
Note: OpenProject Enterprise Edition includes its own MCP server. If you have an Enterprise license, use the official Enterprise MCP instead of this one.
OPENPROJECT_READ_PROJECTS is configuredOPENPROJECT_WRITE_PROJECTS — that allowlist, not the category flags, is the real gate; personal-data and admin writes stay opt-in separatelyA core reason to use this MCP instead of calling the OpenProject REST API directly: it returns context-frugal responses instead of raw HAL payloads — and not just for listing. The numbers below are measured against the same three representative work packages (real tiktoken counts, not a bytes/4 approximation); read/search/write/batch calls all land in the same −85% to −98% range. For the full per-call-type breakdown, the tool-catalog size numbers, and how to reproduce them, see Context efficiency.
This quickstart requires pipx; see Installation if it isn't installed yet.
pipx install openproject-ce-mcp
openproject-ce-mcp configure
openproject-ce-mcp --version
Already use uv? uv tool install openproject-ce-mcp works the same way.
See Installation
for when plain pip install is appropriate instead, and for uvx (a
zero-install, run-on-demand alternative to installing at all).
configure collects your OpenProject URL, API token, and project scope, then
writes the config for the MCP client(s) you choose. Project-scoped is
recommended: the server is then available only in the current project.
Global makes it available everywhere. Restart your MCP client afterward,
then ask it to call get_current_user or list_projects to verify.
See Installation for requirements, updating, source installs, and uninstalling, and Clients for per-client setup guides.
Full documentation lives in docs/, starting at the
documentation hub:
Your client config (.mcp.json, .codex/config.toml, or .vscode/mcp.json)
contains your API token — treat it like a password and keep it out of version
control; choose your client-specific guide from Clients
for the exact .gitignore step. configure writes a minimal config: only the values that differ from a
safe default. Read tools are registered by default, and so are the 5 core
write categories — but project access stays denied either way until you list
projects in OPENPROJECT_READ_PROJECTS (and, for writes, in
OPENPROJECT_WRITE_PROJECTS too); that allowlist pair, not the category
flags, is the real gate.
See Configuration for the full environment variable
reference and what configure --quick vs. --advanced ask.
User-provided text (work-package descriptions, comments, news, wiki content) is marked with <user-content> tags and flagged in server instructions as untrusted. Agents should treat this content as data, not as instructions.
See SECURITY.md for the full security model, including prompt injection mitigations, reporting procedures, and supported versions.
main is a frozen snapshot of the last release, not the active development
branch. See CONTRIBUTING.md for which branch to clone
(active development vs. bugfixes) and the full test suite (unit,
integration, and Docker test instances).
MIT — see LICENSE. A single top-level license file covers the whole project; individual source files don't carry per-file copyright headers, matching common practice for MIT-licensed Python packages.
MCP server for OpenProject Community Edition: projects, work packages, time tracking, meetings, wiki and more as preview-first tools for AI agents such as Claude Code, Codex and GitHub Copilot.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Openproject Ce 透過 stdio 在本機執行。
上次檢查時間:2026-11-14。 MCP server for OpenProject Community Edition: projects, work packages, time tracking, meetings, wiki and more as preview-first tools for AI agents such as Claude Code, Codex and GitHub Copilot.