What are the prerequisites for running the server?
Node.js v18 or higher, a registered Lark/Feishu application with appropriate permissions, and a user access token for calendar operations.
@junyuan-qi
基本情報
概要はまだありません
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Lark MCP Server is a Model Context Protocol (MCP) server implementation for Lark/Feishu. It bridges AI models with Lark’s collaboration platform, enabling MCP‑compatible applications to send messages, manage calendar events, and interact with Lark services.
Clone the repository, install dependencies (npm install), and build (npm run build). Then configure an MCP client—such as Claude Desktop—by adding the server to its claude_desktop_config.json with the required environment variables (LARK_APP_ID, LARK_APP_SECRET, LARK_USER_ID, LARK_CALENDAR_ID, LARK_USER_ACCESS_TOKEN). Restart the client to connect.
Node.js v18 or higher, a registered Lark/Feishu application with appropriate permissions, and a user access token for calendar operations.
It uses the standard I/O (stdio) transport layer. MCP clients launch the server as a child process and communicate through its stdin and stdout channels.
Add the server configuration to `claude_desktop_config.json`, providing the correct path to the built `index.js` and the required environment variables. Then restart Claude Desktop completely.
Check server logs (written to stderr). Common causes include missing environment variables, expired access tokens, insufficient Lark application permissions, or invalid request parameters.
Authentication is handled via environment variables: Lark app credentials (`LARK_APP_ID`, `LARK_APP_SECRET`) and a user access token (`LARK_USER_ACCESS_TOKEN`).
Let your agents read, send and react to email autonomously, without human involvement

Messaging rooms for AI agents: hand off context across tools, worktrees, machines, and teammates. Agents meet in shared rooms over MCP, hand off directly, and leave a replayable transcript; live sessions wake on reply, b

Send, receive and track real faxes in the US and Canada from Claude, ChatGPT or Cursor.

Connect an AI assistant to one Vocenya business account: list calls, leads, bookings and chats, add leads, queue compliant AI callbacks and update Do Not Call.https://github.com/gadyamedia/vocenya-mcp
SendRaven is email infrastructure for AI agents. Send, read replies as threads, run campaigns and automations, with limits on the API key.
コメント