A powerful bridge connecting AI agents to the Lark and FeiShu ecosystem via the Model Context Protocol (MCP).
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mcp-lark
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install mcp-lark using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
This skill leverages the Lark/FeiShu OpenAPI MCP server to give AI agents direct access to your professional workspace. By integrating with Openclaw Skills, developers can enable agents to manage user information, send emails, interact with chat messages, and manipulate cloud documents or multidimensional tables programmatically.
It serves as a unified interface for Lark and FeiShu users who want to automate their daily workflows within a secure and standardized protocol. The integration relies on the mcporter utility to bridge local agent commands with the remote Lark MCP platform, ensuring that Openclaw Skills can execute complex tasks across the entire suite of Lark productivity tools.
First, obtain your MCP service URLs from the Lark or FeiShu documentation. Then, configure your environment variables in your workspace .env file or system settings.
# Configure multiple MCP service URLs and usage scenarios
LARK_MCP_SERVERS='open.larksuite.com/mcp/stream/xxx:Chats and Mails;open.larksuite.com/mcp/stream/yyy:Cloud documents;'
To list available tools for a specific stream, use:
npx -y mcporter list 'open.larksuite.com/mcp/stream/<token>' --all-parameters
To call a specific tool:
npx -y mcporter call 'open.larksuite.com/mcp/stream/<token>.<tool_name>' param1:"value1"
The skill organizes data primarily through the Lark/FeiShu OpenAPI structure. Configuration is stored in environment variables, while tool schemas are fetched dynamically from the remote MCP stream.
| Attribute | Description |
|---|---|
| LARK_MCP_SERVERS | A semicolon-separated list of MCP URLs and their functional descriptions. |
| mcporter | The node-based utility used as the primary binary for execution. |
| Tool Schema | Dynamic JSON structure defining inputs like chat_id, text, or document_uid. |
Loading
A bridge for AI agents to interact with Home Assistant devices and states via the Model Context Protocol.

A high-fidelity text-to-speech engine leveraging Microsoft Edge's neural voices for natural-sounding audio generation.

A high-performance local audio transcription tool powered by faster-whisper for seamless speech-to-text processing.

A comprehensive toolkit for building, testing, and deploying smart contracts on the Polygon PoS network using the Foundry framework.

A versatile media discovery skill that enables AI agents to find video content and cast it directly to smart TVs.

A powerful automation tool for AI agents to post images to Instagram using residential proxies to bypass bot detection.








































