Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AIFire in da houseCheck it out free

lark-mcp-server

MCP.Pizza Chef: junyuan-qi

Lark MCP Server is a Model Context Protocol server that integrates AI models with Lark's collaboration platform. It enables AI assistants to send messages, manage calendar events, and add attendees within Lark. Using stdio transport, it supports seamless communication with MCP clients, facilitating real-time AI-driven workflows in Lark's environment. This server bridges AI capabilities with Lark's messaging and scheduling tools, enhancing automation and collaboration.

Use This MCP server To

Send direct messages to Lark users via AI models Retrieve calendar events within specified time ranges Create new calendar events with detailed customization Add attendees including users, groups, and external emails to events Automate scheduling workflows inside Lark using AI Integrate AI-driven notifications and reminders in Lark chats

README

Lark MCP Server

A Model Context Protocol (MCP) server implementation for Lark/Feishu, enabling MCP-compatible applications to interact with Lark's various collaboration capabilities.

Overview

Lark MCP Server provides a bridge between AI models and Lark's collaboration platform by implementing the Model Context Protocol (MCP) specification. This server allows AI assistants to:

  • Send messages to Lark users
  • Retrieve calendar events
  • Create new calendar events
  • Add attendees to calendar events

The server uses the standard I/O (stdio) transport layer to communicate with MCP clients, making it compatible with various AI model implementations that support the MCP standard.

Features

  • Message Sending: AI models can send direct messages to Lark users
  • Calendar Management:
    • List events within a specific time range
    • Create new calendar events with customizable details
    • Add various types of attendees to events (users, groups, meeting rooms, external emails)

Prerequisites

  • Node.js v18 or higher
  • A registered Lark/Feishu application with appropriate permissions
  • User access token for calendar operations

Installation

  1. Clone the repository:

    git clone https://github.com/junyuan-qi/lark-mcp-server.git
    cd lark-mcp-server
  2. Install dependencies:

    npm install
  3. Build the project:

    npm run build

Usage

Connecting with an MCP Client

The server communicates via standard input/output (stdio). MCP clients can connect to the server by launching it as a child process and communicating through its stdin/stdout channels.

Setting Up with Claude Desktop

You can integrate this MCP server with Claude Desktop by configuring the Claude Desktop application to recognize and use the Lark MCP server.

1. Configure Claude Desktop to recognize the Lark MCP server

You can find claude_desktop_config.json inside the settings of Claude Desktop app:

  1. Open the Claude Desktop app and enable Developer Mode from the top-left menu bar.
  2. Once enabled, open Settings (also from the top-left menu bar) and navigate to the Developer Option, where you'll find the Edit Config button. Clicking it will open the claude_desktop_config.json file, allowing you to make the necessary edits.

Alternatively, you can open claude_desktop_config.json directly from terminal:

For macOS:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

For Windows:

code %APPDATA%\Claude\claude_desktop_config.json

2. Add the Lark MCP server configuration

Add the following configuration to the mcpServers section of your claude_desktop_config.json:

{
  "mcpServers": {
    "lark-mcp-server": {
      "command": "node",
      "args": ["/path/to/lark-mcp-server/build/index.js"],
      "env": {
        "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"
      }
    }
  }
}

Replace the path and environment variables with your actual values. This configuration tells Claude Desktop how to launch the Lark MCP server and what environment variables to provide.

3. Restart Claude Desktop

For the changes to take effect:

  1. Completely quit Claude Desktop (not just close the window)
  2. Start Claude Desktop again
  3. Look for an icon in the UI to verify the Lark MCP server is connected

Once connected, Claude will be able to send messages to Lark users and manage calendar events on your behalf.

Development

Project Structure

  • src/index.ts: Main server implementation
  • build/: Compiled JavaScript files
  • package.json: Project dependencies and scripts

Building

npm run build

This compiles the TypeScript code to JavaScript in the build directory and sets executable permissions.

Troubleshooting

Check the server logs (written to stderr) for detailed error information. Common issues include:

  • Missing environment variables
  • Incorrect or expired access tokens
  • Insufficient permissions for the Lark application
  • Invalid request parameters

License

ISC

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.


For more information about the Model Context Protocol, visit the MCP Documentation.

For more information about Lark/Feishu API, visit the Lark Open Platform Documentation.

lark-mcp-server FAQ

How does Lark MCP Server communicate with AI models?
It uses the standard I/O (stdio) transport layer to interact with MCP clients, enabling compatibility with various AI model implementations.
Can the Lark MCP Server create calendar events?
Yes, it supports creating new calendar events with customizable details.
What types of attendees can be added to calendar events?
Attendees can include Lark users, groups, meeting rooms, and external email addresses.
Is the Lark MCP Server limited to messaging only?
No, it also supports calendar event retrieval, creation, and attendee management.
What collaboration features does the Lark MCP Server expose?
It exposes messaging and calendar management capabilities within Lark.
Can this server be used with different AI providers?
Yes, it is compatible with any MCP client and supports AI models from providers like OpenAI, Claude, and Gemini.
How does this server enhance AI workflows in Lark?
By enabling AI models to interact directly with Lark's messaging and calendar APIs, it automates communication and scheduling tasks.