This project provides a Model Context Protocol (MCP) server that enables AI-driven coding tools like Cursor, Windsurf, and Cline to access, edit, and structurally process Feishu documents. It allows AI to directly understand and interact with Feishu content, significantly boosting efficiency for developers and power users who integrate Feishu into their AI-assisted workflows.

How It Works

The project implements an MCP server that bridges AI coding tools with Feishu's document ecosystem. It offers structured, chunked, and rich text retrieval, enabling AI to accurately interpret document context. Key functionalities include folder directory acquisition, content fetching and understanding, intelligent document and block creation/editing, and efficient keyword-based search within Feishu documents. This approach allows AI tools to leverage Feishu's real-world document structures and content seamlessly.

Quick Start & Requirements

Installation can be done via NPM (npx feishu-mcp@latest ...) or by cloning the repository (git clone https://github.com/cso1z/Feishu-MCP.git, cd Feishu-MCP, pnpm install, pnpm run dev). A mandatory Feishu application configuration with App ID and App Secret is required. Local setup involves pnpm and environment variable configuration (.env file). Links to official Feishu tutorials and a detailed FEISHU_CONFIG.md are provided for setup.

Highlighted Details

• Comprehensive Document Operations: Supports creating/getting documents and blocks, batch operations, and folder management.
• Rich Content Support: Handles markdown, code blocks with syntax highlighting, lists, images (local/remote), LaTeX formulas, Mermaid diagrams, and complex tables.
• Flexible Authentication: Offers both tenant (application-level) and user (user-level via OAuth) access tokens.
• AI Tool Integration: Designed for seamless integration with AI coding environments via the MCP protocol.

Maintenance & Community

The project encourages community contributions through stars, bug reports, feature suggestions, documentation improvements, and pull requests. Specific community channels or contributor details are not provided in the README.

Licensing & Compatibility

The README does not specify the project's license, which is a critical omission for assessing commercial compatibility or usage restrictions.

Limitations & Caveats

Mandatory Feishu application setup is required. Image uploads in server environments are limited to URLs due to parameter length constraints. User authentication requires careful permission management and URL parameterization (userKey). The absence of explicit licensing information poses an adoption risk.