Lark(Feishu) MCP Server

What does “Lark(Feishu)” MCP Server do?

The Lark(Feishu) MCP Server is a Model Context Protocol (MCP) implementation designed to connect AI assistants with Lark (also known as Feishu), a popular collaborative office suite. This server enables AI-driven workflows to interact with Lark sheets, messages, documents, and more. By providing a standardized interface, it allows AI models to perform actions such as writing data to Lark spreadsheets, making it possible to automate data entry, reporting, or collaborative tasks. The integration enhances development workflows by bridging AI capabilities with real-time document management, streamlining interactions with Lark’s ecosystem for tasks that would otherwise require manual intervention.

List of Prompts

No prompt templates were mentioned in the repository.

List of Resources

No specific resources are listed in the repository.

List of Tools

• write_excel
  Write data to a sheet in a Lark(Feishu) sheet and return a link. Requires an email address to add as an access permission.

Use Cases of this MCP Server

• Automated Data Entry:
  Developers can set up workflows where AI automatically writes structured data into Lark spreadsheets, reducing manual input and potential errors.
• Collaborative Report Generation:
  The server can be used to generate reports in Lark sheets, making them instantly available for team collaboration and review.
• Integrating Lark with AI Agents:
  By exposing Lark sheets as writable resources, developers can build AI agents that log results, track metrics, or manage project sheets directly from code or chat interfaces.
• Workflow Automation:
  Routine business operations, such as updating attendance sheets or inventory lists, can be automated via AI using this server.

How to set it up

Windsurf

1. Prerequisite: Ensure you have Node.js and Windsurf installed.

2. Create a Lark(Feishu) App:
   Visit Lark Open Platform and create an app.

3. Apply Permissions:
   Grant the app sheets:spreadsheet:readonly permission.

4. Set Environment Variables:
   Set LARK_APP_ID and LARK_APP_SECRET in your environment.

5. Configure in Windsurf:
   Edit your configuration file to add the MCP server:

   "mcpServers": {
     "mcpServerLark": {
       "description": "MCP Server For Lark(Feishu)",
       "command": "uvx",
       "args": [
         "parent_of_servers_repo/servers/src/mcp_server_lark"
       ],
       "env": {
         "LARK_APP_ID": "xxx",
         "LARK_APP_SECRET": "xxx"
       }
     }
   }
   

6. Save and Restart:
   Save the config, restart Windsurf, and verify the connection.

Claude

1. Prerequisite: Ensure Claude supports MCP server integration.
2. Create and configure your Lark App as above.
3. Add MCP Server to Claude settings:
   Insert the JSON snippet into Claude’s MCP configuration.
4. Secure credentials using environment variables as shown above.
5. Restart and verify integration.

Cursor

1. Install Cursor and set up Node.js.
2. Create your Lark(Feishu) App and set the required permissions.
3. Add the MCP server to Cursor’s configuration:
   Use the same JSON configuration as above.
4. Set environment variables for API keys.
5. Restart Cursor and check for MCP server presence.

Cline

1. Set up Cline and Node.js.

2. Register and configure your Lark(Feishu) app with permissions.

3. Add the following to your Cline configuration:

   "mcpServers": {
     "mcpServerLark": {
       "description": "MCP Server For Lark(Feishu)",
       "command": "uvx",
       "args": [
         "parent_of_servers_repo/servers/src/mcp_server_lark"
       ],
       "env": {
         "LARK_APP_ID": "xxx",
         "LARK_APP_SECRET": "xxx"
       }
     }
   }
   

4. Save and restart Cline.

5. Test connection to confirm setup.

Securing API Keys

Always use environment variables to store sensitive configuration values such as API keys. Example:

"env": {
  "LARK_APP_ID": "your_app_id",
  "LARK_APP_SECRET": "your_app_secret"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "lark-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “lark-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the content found, this MCP server is in a very early stage, with minimal tooling and documentation. It primarily exposes a single tool and lacks details on prompts or resources. The configuration instructions are clear but basic. For now, the server scores low in terms of completeness and usability for broader MCP workflows.

MCP Score