lark
MCP server from junyuan-qi/lark-mcp-server
claude mcp add --transport stdio junyuan-qi-lark-mcp-server node build/index.js \ --env LARK_APP_ID="your_app_id" \ --env LARK_USER_ID="target_user_id" \ --env LARK_APP_SECRET="your_app_secret" \ --env LARK_CALENDAR_ID="target_calendar_id" \ --env LARK_USER_ACCESS_TOKEN="your_user_access_token"
How to use
The Lark MCP Server provides a bridge between AI models and the Lark/Feishu collaboration platform using the Model Context Protocol (MCP) over standard input/output. It enables AI agents to perform common collaboration tasks by sending MCP requests through the server process and receiving responses via stdout. The server supports message delivery to Lark users and calendar management operations, including listing calendar events, creating new events, and attaching attendees to events. This makes it possible to integrate Lark-enabled capabilities into model workflows, chat assistants, or orchestration systems that implement MCP.
How to install
Prerequisites:
- Node.js v18 or higher
- NPM (comes with Node.js)
- Access to a registered Lark/Feishu application with the necessary permissions
Installation steps:
-
Clone the repository git clone https://github.com/junyuan-qi/lark-mcp-server.git cd lark-mcp-server
-
Install dependencies npm install
-
Build the project npm run build
-
Run the server (example) npm start // or execute the built file directly if you prefer node build/index.js
Environment setup (required for Lark operations):
- Set up environment variables (see mcp_config for placeholders): LARK_APP_ID="your_app_id" LARK_APP_SECRET="your_app_secret" LARK_USER_ID="target_user_id" LARK_CALENDAR_ID="target_calendar_id" LARK_USER_ACCESS_TOKEN="your_user_access_token"
Additional notes
Tips and common issues:
- Ensure the Lark app has the correct permissions for messaging and calendar access.
- Confirm that the provided tokens and IDs are valid and not expired.
- If you encounter initialization errors, check that all required environment variables are set.
- The MCP transport is stdio; integrate this server by spawning it as a child process and wiring requests/responses to its stdin/stdout.
- When deploying with Claude Desktop or other MCP clients, provide the build/index.js path and environment variables in the client configuration (as shown in the example claude_desktop_config.json snippet).
- For troubleshooting, inspect logs written to stderr for error messages related to authentication, permissions, or invalid request parameters.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.