Overview
What is Feishu Mcp?
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).
How to use Feishu Mcp?
Install dependencies with npm install, then build with npm run build. Run the server in stdio mode using node dist/index.js --config '{"appId":"xxx","appSecret":"xxx"}' or in SSE mode by adding the --sse flag. You need a Feishu app with valid appId and appSecret credentials.
Key features of Feishu Mcp
- 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
Use cases of Feishu Mcp
- Automate data entry into Feishu bitables based on AI model decisions
- Update existing records in a Feishu bitable from AI-driven workflows
- Search and retrieve specific records from a Feishu bitable
- Manage the structure of Feishu bitable apps and their tables programmatically
FAQ from Feishu Mcp
What does Feishu Mcp do?
Feishu Mcp enables AI models to perform operations on Feishu bitables by exposing MCP tools that call Feishu APIs.
What transport modes are supported?
The server can run in stdio mode (standard input/output) or SSE mode (Server-Sent Events over HTTP).
What are the runtime dependencies?
You need Node.js and npm to install and run the server. You also require a Feishu app with appId and appSecret for API authentication.
Does Feishu Mcp support all Feishu APIs?
Currently the implementation primarily supports bitable (multidimensional table) operations. Full Feishu API coverage is not yet available.
How do I configure the server?
Pass a JSON config string with appId and appSecret via the --config argument when starting the server.
