Feishu
A remote Model Context Protocol server for Feishu (Lark) that supports OAuth authentication and deployment on Cloudflare Workers. It allows AI clients to interact with Feishu documents, perform content searches, and manage document blocks with a zero
What is Feishu?
Feishu is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to remote model context protocol server for feishu (lark) that supports oauth authentication and deployment on cloudflare workers. it allows ai clients to interact with feishu documents, perform content ...
A remote Model Context Protocol server for Feishu (Lark) that supports OAuth authentication and deployment on Cloudflare Workers. It allows AI clients to interact with Feishu documents, perform content searches, and manage document blocks with a zero
This server falls under the Business Applications and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A remote Model Context Protocol server for Feishu (Lark) tha
Use Cases
Maintainer
Works with
Installation
NPM
npx -y feishu-mcpManual Installation
npx -y feishu-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Feishu
The Feishu MCP Server connects AI coding tools such as Cursor, Claude Desktop, Windsurf, and Cline to Feishu (Lark) documents and task management through the Model Context Protocol. It supports reading, creating, and editing document blocks, searching documents, managing folders, handling wikis, uploading images, and creating Mermaid diagrams — with full task management (create, update, delete, sub-tasks) and user lookup available when using user-level authentication. The server is published to npm as feishu-mcp and can be run without any local build step.
Prerequisites
- Node.js 18 or higher (for npx)
- A Feishu (Lark) developer account at open.feishu.cn
- A Feishu app with App ID and App Secret (create one at open.feishu.cn/app)
- Document and task permissions configured in your Feishu app settings
- An MCP client such as Claude Desktop, Cursor, or Cline
Create a Feishu app and obtain credentials
Log in to open.feishu.cn, create a new app, and note the App ID and App Secret. Follow the Feishu developer documentation to enable the required document, folder, and task read/write permissions for your app.
Add the bot to your Feishu workspace
In your app settings on open.feishu.cn, publish the app to your workspace so it can access documents and tasks. For user-level authentication (task management, user search), you will also need to configure OAuth.
Run the MCP server via npx
You can run the server directly with npx, passing your credentials as arguments. Choose 'tenant' auth type for app-level access or 'user' for task management features.
npx feishu-mcp@latest \
--feishu-app-id=cli_your_app_id \
--feishu-app-secret=your_app_secret \
--feishu-auth-type=tenant \
--enabled-modules=document,taskAdd to your MCP client configuration
Add the feishu-mcp server to your MCP client config file. Pass your Feishu credentials as environment variables or command-line arguments.
{
"mcpServers": {
"feishu": {
"command": "npx",
"args": ["-y", "feishu-mcp"],
"env": {
"FEISHU_APP_ID": "cli_your_app_id",
"FEISHU_APP_SECRET": "your_app_secret",
"FEISHU_AUTH_TYPE": "tenant",
"FEISHU_ENABLED_MODULES": "document,task"
}
}
}
}Verify connection and test document access
Restart your MCP client and confirm the Feishu server is listed as connected. Ask your AI assistant to list documents in a folder or fetch a specific document to verify access.
Feishu Examples
Client configuration
Claude Desktop configuration for the Feishu MCP server using environment variables for credentials.
{
"mcpServers": {
"feishu": {
"command": "npx",
"args": ["-y", "feishu-mcp"],
"env": {
"FEISHU_APP_ID": "cli_your_app_id",
"FEISHU_APP_SECRET": "your_app_secret",
"FEISHU_AUTH_TYPE": "tenant",
"FEISHU_ENABLED_MODULES": "document,task"
}
}
}
}Prompts to try
Example prompts for interacting with Feishu documents and tasks through your AI assistant.
- "List all documents in my Feishu project folder"
- "Create a new Feishu document titled 'Sprint Planning' with a table of tasks"
- "Search my Feishu workspace for documents about API design"
- "Add a Mermaid flowchart to the document at this URL: https://..."
- "Create a task assigned to [name] with due date next Friday"Troubleshooting Feishu
MCP server connects but document operations fail with permission errors
Your Feishu app must have explicit read and write permissions for docs, drive, and tasks configured in the app settings on open.feishu.cn. The app must also be installed to your Feishu workspace. Check that FEISHU_ENABLED_MODULES matches the permissions granted.
Task management tools are not available or return authentication errors
Task management and user search require user-level authentication (FEISHU_AUTH_TYPE=user). Switch to user auth mode and complete the OAuth flow. The server will open a browser window for authorization on first use in user mode.
Scope validation errors on startup
Set the environment variable FEISHU_SCOPE_VALIDATION=false to disable scope checking if your app has a non-standard permission configuration. This can also be passed as --feishu-scope-validation=false on the command line.
Frequently Asked Questions about Feishu
What is Feishu?
Feishu is a Model Context Protocol (MCP) server that remote model context protocol server for feishu (lark) that supports oauth authentication and deployment on cloudflare workers. it allows ai clients to interact with feishu documents, perform content searches, and manage document blocks with a zero It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Feishu?
Install via npm with the command: npx -y feishu-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Feishu?
Feishu works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Feishu free to use?
Yes, Feishu is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Feishu Alternatives — Similar Business Applications Servers
Looking for alternatives to Feishu? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Feishu in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Feishu?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.