Lark

by lorrylockie

2 stars
66 downloads
Not rated
GitHub

About

Provides a bridge to Lark/Feishu workplace collaboration platform, enabling access to employee information and messaging capabilities with automatic authentication and token management.

Details

Author
lorrylockie
Repository
lorrylockie/lark-mcp
GitHub stars
2
Downloads
66
Categories
Design, Workplace, Developer Tools, AI, Communication, Knowledge Base, API
Tags
#integration

- Query employee information using Lark's Contact API
- More features coming soon...

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Lark
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 lark-mcp
    Environment
    • LARK_APP_ID your_app_id
    • LARK_APP_SECRET your_app_secret

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

The server prioritizes credentials in the following order:
1. Command line arguments
2. Environment variables
3. Default values (if any)

export LARK_APP_ID=your_app_id
export LARK_APP_SECRET=your_app_secret
npx lark-mcp

get-user-info

Retrieves employee information using their ID.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "lark": {
            "env": {
                "LARK_APP_ID": "your_app_id",
                "LARK_APP_SECRET": "your_app_secret"
            },
            "args": [
                "lark-mcp"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": {
        "LARK_APP_ID": "your_app_id",
        "LARK_APP_SECRET": "your_app_secret"
    },
    "args": [
        "lark-mcp"
    ],
    "command": "npx"
}

Macos

{
    "env": {
        "LARK_APP_ID": "your_app_id",
        "LARK_APP_SECRET": "your_app_secret"
    },
    "args": [
        "lark-mcp"
    ],
    "command": "npx"
}

Windows

{
    "env": {
        "LARK_APP_ID": "your_app_id",
        "LARK_APP_SECRET": "your_app_secret"
    },
    "args": [
        "/c",
        "npx",
        "lark-mcp"
    ],
    "command": "cmd"
}

Lark MCP Server

A Model Context Protocol (MCP) server that integrates with Lark/Feishu APIs, allowing LLMs to interact with Lark services.

Features

- Query employee information using Lark's Contact API
- More features coming soon...

Prerequisites

- Node.js 16 or higher
- A Lark/Feishu application with App ID and App Secret
- Claude for Desktop or another MCP client

Installation

npm install
npm run build

Usage

You can run the server in two ways:

1. Using Command Line Arguments (Recommended)

npx lark-mcp <app_id> <app_secret>

Replace <app_id> and <app_secret> with your Lark application credentials.

2. Using Environment Variables

export LARK_APP_ID=your_app_id
export LARK_APP_SECRET=your_app_secret
npx lark-mcp

Available Tools

get-user-info

Retrieves employee information using their ID.

Example usage in Claude:

Please look up employee information for ID 12345

Development

1. Clone the repository
2. Install dependencies:

   npm install

3. Build the project:
   npm run build

4. Start the server in development mode:
   npm run dev

Configuration

The server prioritizes credentials in the following order:
1. Command line arguments
2. Environment variables
3. Default values (if any)

Error Handling

- The server will validate credentials before starting
- API errors are properly handled and returned to the client
- Detailed error messages help with troubleshooting

License

MIT

Contributing

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Create a new Pull Request

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.