📌Overview

Purpose: This framework aims to facilitate the integration between Feishu and AI encoding agents for various document-related operations.

Overview: The MCP server serves as a bridge to deliver Feishu-related functionalities to artificial intelligence applications. It allows LLMs (Large Language Models) to perform tasks such as reading documents, sending messages, managing contract approvals, and processing data, potentially uncovering innovative combinations of these capabilities.

Key Features:

• Feishu Integration: Enables seamless interaction with Feishu for document reading, message sending, and data processing, enhancing productivity and automation for AI agents.

• Application Setup and Authorization: Provides a structured process for creating and configuring applications, including necessary token handling and document authorization, ensuring secure access to Feishu resources.

---

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、数据处理等功能，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发布，具体步骤请参考飞书官方文档：https://open.feishu.cn/document/server-docs/api-call-guide/terminology

完成应用创建后，需要对应用进行文档授权，这一步较为繁琐，参考官方方案：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. 将 MCP 添加到 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

tools

get_feishu_doc

获取飞书文档信息（纯文本）