Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

lark-tools-mcp

MCP.Pizza Chef: Li-vien

lark-tools-mcp is an MCP server that integrates Feishu (飞书) operations with AI agents like cursor. It enables AI models to read Feishu documents, send messages, handle contract approvals, and process data by bridging Feishu's platform with LLMs. This server requires a Feishu self-built application with proper authorization and token-based authentication to operate, facilitating seamless AI-driven workflows within the Feishu ecosystem.

Use This MCP server To

Read and extract text from Feishu documents for analysis Send messages within Feishu via AI-driven commands Automate contract approval workflows in Feishu Process and manipulate Feishu data through AI agents Integrate Feishu document content into AI-powered summaries Enable AI agents to interact with Feishu workspace tools Bridge Feishu platform with LLMs for enhanced collaboration

README

lark-tools-mcp

MCP server provides Feishu related operations to AI encoding agents such as cursor
飞书MCP插件
通过打通飞书与cursor，向LLM提供读取文档、发送消息、合同审批、数据处理.....
可能会有意想不到的组合方式

创建自建应用

MCP服务运行基于token，需要创建一个应用并做发布 https://open.feishu.cn/document/server-docs/api-call-guide/terminolog

然后对应用进行文档授权，这一步较为繁琐，参考文档，选择合适的方案：https://open.feishu.cn/document/uAjLw4CM/ugTN1YjL4UTN24CO1UjN/trouble-shooting/how-to-add-permissions-to-app

运行服务

  1. 拷贝 .env.example 为 .env 文件
  2. 修改 .env 文件中的 FEISHU_APP_ID 为飞书自建应用的 app_id
  3. 修改 .env 文件中的 FEISHU_APP_SECRET 为飞书自建应用的 app_secret
  4. 运行 MCP Server
    yarn install yarn start
  5. Add MCP to cursor
  6. Agent 模式下，输入飞书文档链接，让AI帮你阅读与整理内容

效果

tools

get_feishu_doc

获取飞书文档信息（纯文本）

lark-tools-mcp FAQ

How do I authenticate the lark-tools-mcp server with Feishu?
You must create a Feishu self-built application, obtain the app_id and app_secret, and configure them in the .env file for token-based authentication.
What permissions are required for the Feishu app to work with lark-tools-mcp?
The app needs document read permissions and messaging scopes; detailed authorization steps are in Feishu's official documentation linked in the README.
Can lark-tools-mcp handle contract approvals automatically?
Yes, it supports contract approval workflows by leveraging Feishu's APIs integrated into the MCP server.
Is it possible to use lark-tools-mcp with AI models other than cursor?
Yes, while designed for cursor, it can work with any LLM that supports MCP protocol, including OpenAI, Claude, and Gemini.
How do I deploy and run the lark-tools-mcp server?
Clone the repo, copy .env.example to .env, set your Feishu app credentials, then run 'yarn install' and 'yarn start' to launch the server.
What kind of Feishu documents can lark-tools-mcp read?
It can read and extract plain text from various Feishu document types accessible via the authorized app.
Can I extend lark-tools-mcp with additional Feishu API features?
Yes, the server is modular and can be extended to support more Feishu operations as needed.
Does lark-tools-mcp support real-time interaction with Feishu?
It supports real-time document reading and messaging through API calls, enabling dynamic AI interactions within Feishu.