Feishu

by darknoah

6 stars
550 downloads
Not rated
GitHub

About

Feishu Mcp is an implementation of the Model Context Protocol (MCP) for Feishu (Lark) applications. It allows AI models to interact with Feishu APIs through tool calls, currently focusing on operations for bitable (multidimensional tables).

Details

Author
darknoah
Repository
DarkNoah/feishu-mcp
GitHub stars
6
Downloads
550
License
MIT License
Categories
AI, Infrastructure, Communication
Tags
#integration

- Built on the Model Context Protocol TypeScript SDK
- Provides tools for creating, updating, searching, and deleting bitable records
- Supports listing fields and creating new bitable apps and tables
- Communicates via HTTP+SSE or stdio transport

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 Feishu
    Command (node, npx, python, etc.) node
    Arguments
    • Argument 1 dist/index.js
    • Argument 2 --config
    • Argument 3 {"appId":"xxx","appSecret":"xxx"}

    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

npm install

create_record

在飞书多维表格中创建一条新记录

update_record

在飞书多维表格中更新一条记录

list_fields

获取多维表格数据表中的的所有字段

search_records

在多维表格中搜索符合条件的记录

delete_record

删除多维表格中的一条记录

create_bitable_app

创建一个新的飞书多维表格应用

create_table

创建飞书多维表格中的一个新数据表

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "feishu": {
            "env": {},
            "args": [
                "dist/index.js",
                "--config",
                "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"
            ],
            "shell": false,
            "command": "node"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "dist/index.js",
        "--config",
        "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"
    ],
    "shell": false,
    "command": "node"
}

Macos

{
    "env": [],
    "args": [
        "dist/index.js",
        "--config",
        "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"
    ],
    "shell": false,
    "command": "node"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "node",
        "dist/index.js",
        "--config",
        "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"
    ],
    "shell": false,
    "command": "cmd"
}

飞书 MCP 服务器

这是一个为飞书(Feishu/Lark)应用提供Model Context Protocol (MCP) 服务的实现,允许AI大模型通过工具调用与飞书API进行交互,目前主要支持多维表格操作。

功能特性

- 基于Model Context Protocol (MCP) TypeScript SDK
- 提供飞书多维表格操作工具
- 支持HTTP+SSE通信

已实现工具

create_record

在飞书多维表格中创建一条新记录

update_record

在飞书多维表格中更新一条记录

list_fiedls

获取多维表格数据表中的的所有字段

search_records

在多维表格中搜索符合条件的记录

delete_record

删除多维表格中的一条记录

create_bitable_app

创建一个新的飞书多维表格应用

create_table

创建飞书多维表格中的一个新数据表

Development

# Install dependencies
npm install

Build

npm run build

Dev

npm run dev

run mcp stdio

node dist/index.js --config "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"

run mcp sse

node dist/index.js --sse --config "{\"appId\":\"xxx\",\"appSecret\":\"xxx\"}"

飞书API参考

- 飞书多维表格API文档
- 创建记录API
- 获取记录API
- 搜索记录API
- 删除记录API
- 创建多维表格应用API
- 创建数据表API
- 列出字段信息

许可证

MIT 29:["$","div",null,{"className":"my-8 pb-8 h-full max-w-5xl mx-auto","children":["$","div",null,{"className":"grid grid-cols-1 md:grid-cols-3 gap-6","children":["$","$L30",null,{"mcp":{"id":"mcp_9uM21enBZPj7","name":"Feishu","description":"Feishu/Lark messaging platform integration.","logo":"https://avatars.githubusercontent.com/darknoah","banner_url":null,"stars":6,"downloads":0,"categories":["ai","infrastructure","integration"],"isRecommended":false,"created_at":"

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.