Lark

A Node.js MCP server that integrates with Lark APIs to query employee information and enable ML-powered interactions.

javascript

3

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lorrylockie-lark-mcp": {
      "command": "npx",
      "args": [
        "lark-mcp",
        "<app_id>",
        "<app_secret>"
      ],
      "env": {
        "LARK_APP_ID": "your_app_id",
        "LARK_APP_SECRET": "your_app_secret"
      }
    }
  }
}

You run an MCP server that enables LLMs to interact with Lark services through a simple command-line interface. With your Lark App ID and App Secret, you can securely query employee information and extend capabilities as you add more features. This guide shows practical steps to install, start, and use the Lark MCP Server with an MCP client.

How to use

To use the Lark MCP Server, run it from your terminal using your Lark application credentials. You can start it directly with your App ID and App Secret on the command line, or provide those credentials via environment variables and start the server without passing them on the command line. Once running, your MCP client can call the available tools to fetch employee information from Lark. The primary tool exposed is get-user-info, which retrieves employee details by their ID.

How to install

Prerequisites you need before installing include Node.js 16 or higher and a Lark/Feishu application with an App ID and App Secret.

# Install dependencies
npm install

# Build the project
npm run build

Starting the server with command line arguments (recommended)

Provide your Lark App ID and App Secret directly on startup. This is the simplest way to run and test the MCP server.

npx lark-mcp <app_id> <app_secret>

Starting the server with environment variables

Set credentials in your environment, then start the MCP server without additional arguments.

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

Notes on usage with MCP clients

The server exposes tools that your MCP client can invoke. The main tool described is get-user-info, which retrieves employee information by ID. Use this in your conversations with the MCP client to look up employees by their unique identifier.

Configuration and credential precedence

Credentials are resolved in this order: command line arguments take precedence over environment variables. If neither is provided, the server will not start with valid credentials. Default values are used only if explicitly defined for a given option.

Security considerations

Keep your App Secret secure. If you deploy in a shared environment, prefer environment variables over command line arguments to avoid leaking credentials in process lists. Rotate App Secrets periodically and restrict access to the running server.

Troubleshooting tips

Verify that Node.js 16+ is installed
Check that LARK_APP_ID and LARK_APP_SECRET are correct
Ensure the server can reach Lark APIs from the host
Review error messages from the MCP client for invalid credentials or network issues

Available tools

get-user-info

Retrieves employee information using their Lark ID by querying the Lark Contact API.