Happy slice of mcp pizzaMCP.pizza

feishu-mcp

MCP.Pizza Chef: DarkNoah

feishu-mcp is a Model Context Protocol (MCP) server implementation for Feishu (Lark) applications, enabling AI large models to interact with Feishu APIs via tool calls. It primarily supports operations on Feishu multidimensional tables, including creating, updating, searching, and deleting records, as well as managing tables and applications. It uses HTTP+SSE communication and is built on the MCP TypeScript SDK.

Use This MCP server To

Create new records in Feishu multidimensional tables Update existing records in Feishu tables via AI commands Search for records matching criteria in Feishu tables Delete records from Feishu multidimensional tables Create new Feishu multidimensional table applications Add new data tables within Feishu multidimensional apps Enable AI models to automate Feishu table data management

README

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

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

feishu-mcp FAQ

How do I configure feishu-mcp to connect with my Feishu app?
You need to provide your Feishu appId and appSecret in the configuration file or command line when running the server.
What communication protocols does feishu-mcp support?
feishu-mcp supports HTTP and Server-Sent Events (SSE) for real-time communication.
Can feishu-mcp handle all Feishu API operations?
Currently, feishu-mcp mainly supports multidimensional table operations like create, update, search, and delete records.
Is feishu-mcp compatible with multiple LLM providers?
Yes, it is designed to work with various LLMs such as OpenAI, Claude, and Gemini through the MCP protocol.
How do I run feishu-mcp in development mode?
After installing dependencies, use 'npm run dev' to start the server in development mode.
Does feishu-mcp provide tools for creating new tables and apps?
Yes, it includes tools to create new multidimensional table apps and tables within Feishu.
Where can I find the Feishu API documentation used by feishu-mcp?
The Feishu multidimensional table API docs are available at https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure.