Bitable MCP

🚀 Bitable MCP Server

This MCP server provides access to Lark Bitable through the Model Context Protocol. It allows users to interact with Bitable tables via predefined tools.

🚀 Quick Start

📦 Installation

One-click Installation and Configuration

Claude

To install and configure the server, use the following command:

PERSONAL_BASE_TOKEN=your_personal_base_token APP_TOKEN=your_app_token uv run --with uv --with bitable-mcp bitable-mcp-install

Replace your_personal_base_token and your_app_token with your actual tokens.

Cursor

Coming soon.

Windsurf

Coming soon.

Manual Installation and Configuration

Make sure you have installed uvx before installation.

Add the following to your Claude settings:

1. Using uvx

"mcpServers": {
  "bitable-mcp": {
    "command": "uvx",
    "args": ["bitable-mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
}

2. Installing via pip

1. Install bitable-mcp via pip:

pip install bitable-mcp

2. Modify your Claude settings

"mcpServers": {
  "bitable-mcp": {
    "command": "python",
    "args": ["-m", "bitable_mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
}

Configuring Zed

Add the following to your Zed settings.json:

Using uvx

"context_servers": [
  {
    "bitable-mcp": {
      "command": "uvx",
      "args": ["bitable-mcp"],
      "env": {
          "PERSONAL_BASE_TOKEN": "your-personal-base-token",
          "APP_TOKEN": "your-app-token"
      }
    }
  }
],

Using pip installation

"context_servers": {
  "bitable-mcp": {
    "command": "python",
    "args": ["-m", "bitable_mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
},

💻 Usage Examples

Available Tools

• list_table - List the current Bitable tables.

  • Returns: A list of table names in JSON format.

• describe_table - Describe a table by name.

  • Parameters:
    • name (str): The name of the table to describe.
  • Returns: A list of columns in JSON format.

• read_query - Execute an SQL query to read data from a table.

  • Parameters:
    • sql (str): The SQL query to execute.
  • Returns: A list of query results in JSON format.

🔧 Debugging

You can use the MCP inspector to debug the server. For uvx installation:

npx @modelcontextprotocol/inspector uvx bitable-mcp