Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Basecamp in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Drive Basecamp 4 (project & team collaboration) from any AI agent: projects, todo lists, todos, messages, comments, people. 12 tools, OAuth2 Bearer auth.
试试这样问
Basecamp 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 → Basecamp、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Basecamp + Gemini
Drive Basecamp 4 (project & team collaboration) from any AI agent: projects, todo lists, todos, messages, comments, people. 12 tools, OAuth2 Bearer auth.
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:
BASECAMP_ACCESS_TOKEN, BASECAMP_ACCOUNT_ID
步骤 1 — 获取凭证
com — github.com/basecamp/bc3-api).
Setup:
- Register an integration at https://launchpad.37signals.com/integrations.
- Implement OAuth2 authorization-code flow with
https://launchpad.37signals.com/authorization(response includes user's account_id). - Set
BASECAMP_ACCESS_TOKENto the obtained access token. - Set
BASECAMP_ACCOUNT_IDto your Basecamp account ID (a 6-9 digit number — visible in any Basecamp URL or returned by the OAuth identity endpoint).
Authentication: Authorization: Bearer ${BASECAMP_ACCESS_TOKEN}.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && 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—Basecamp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 |
|---|---|
basecamp_get_my_profile | Return the authenticated user's profile (id, name, email_address, time_zone, avatar_url, can_manage_projects, etc |
basecamp_list_projects | List active projects (Basecamps) the user has access to |
basecamp_get_project | Fetch a single project with its dock — the array of tools (todoset, message_board, etc |
basecamp_list_todolists | List todolists within a project's todoset |
basecamp_list_todos | List todos in a todolist |
basecamp_create_todo | Create a todo in a todolist |
basecamp_complete_todo | Mark a todo as completed |
basecamp_uncomplete_todo | Reopen a completed todo |
basecamp_list_messages | List messages on the project's message board |
basecamp_post_message | Post a new message on the project's message board |
basecamp_add_comment | Add a comment to a recording (todo, message, document, etc |
basecamp_get_people | List all people in the Basecamp account |
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?
