跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 OpenProject，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
Summary
OpenProject: projects, work packages with their activities, versions, time entries, users and statuses, queried with OpenProject's filter grammar. API v3, Basic auth with the literal username `apikey`.
试试这样问
OpenProject 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → OpenProject、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
OpenProject + Gemini
OpenProject: projects, work packages with their activities, versions, time entries, users and statuses, queried with OpenProject's filter grammar. API v3, Basic auth with the literal username apikey.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
OPENPROJECT_URL, OPENPROJECT_API_KEY
步骤 1 — 获取凭证
Getting a key
- In OpenProject open My Account → Access tokens and generate an API token.
- Set
OPENPROJECT_URLto your instance root (no trailing slash) andOPENPROJECT_API_KEYto the token.
The Basic-auth username is the literal string apikey. Not your login name — the word apikey, with the token as the password. This adapter does it for you, and it is the first thing to check when a token you know is valid returns 401.
Permissions follow the user. The token inherits its owner's project memberships and roles. A project the user is not a member of is simply absent from the results, not an error.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—OpenProject应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
openproject_get_me | Read the user the API token belongs to, with their name, e-mail, language and admin flag |
openproject_list_projects | List projects with their identifier, name, status, description and active flag |
openproject_list_work_packages | List work packages — tasks, bugs, features, milestones — across all projects, with their type, status, assignee, dates and priority |
openproject_list_project_work_packages | List the work packages inside one project — the usual scope for 'what is open on this project' and much cheaper than filtering globally |
openproject_get_work_package | Read one work package in full: description, type, status, assignee, dates, estimated and spent time, and its custom fields |
openproject_list_work_package_activities | Read the activity stream of one work package: every comment and field change in order, with author and timestamp |
openproject_list_time_entries | List logged time entries with their user, work package, date, hours and comment — the raw data behind any effort report |
openproject_list_versions | List versions (releases and sprints) with their name, status, due date and the project they belong to |
openproject_list_users | List users with their name, e-mail, login and status, to resolve who a work package is assigned to |
openproject_list_statuses | List the work-package statuses this instance defines, with their id, name and whether each counts as closed |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
