mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/al-one/mcp-larkWhat This Skill Does
The mcp-lark skill integrates OpenClaw with the Lark/FeiShu ecosystem via the Model Context Protocol (MCP). It acts as a bridge, allowing your AI agent to interact directly with various Lark services, including messaging, email management, cloud documents, multidimensional tables, tasks, and calendars. By leveraging the mcporter utility, the agent can programmatically execute tools provided by remote Lark MCP servers, effectively turning your agent into a powerful administrative assistant that operates directly within your corporate workspace.
Installation
To install this skill, run the following command in your terminal:
clawhub install openclaw/skills/skills/al-one/mcp-lark
Once installed, you must configure your environment variables. Locate the .env file in your workspace and define LARK_MCP_SERVERS. You can map multiple MCP service URLs to specific use cases, such as open.larksuite.com/mcp/stream/xxx:Chats and Mails. If these variables are not found, the agent will prompt you to provide the necessary configuration settings.
Use Cases
This skill is designed for professionals who rely on the Lark/FeiShu suite for daily operations. Use cases include:
- Automated Communication: Drafting and sending messages, or retrieving unread emails.
- Content Management: Interacting with cloud documents or updating rows in multidimensional tables.
- Scheduling: Querying your calendar for upcoming events or creating new meeting entries.
- Task Orchestration: Managing task lists and tracking project progress within the Lark platform.
Example Prompts
- "Check my Lark calendar for today and summarize my upcoming meetings."
- "Draft a message to the team channel about the project status update based on the document at [link]."
- "Find the last three emails from my manager and provide a concise summary of the action items."
Tips & Limitations
- Configuration First: Always ensure your MCP tokens are correctly mapped in the
LARK_MCP_SERVERSenvironment variable before attempting to call tools. - Use
mcporter: Always prefix your commands withnpx -y mcporterto ensure compatibility and leverage the latest tool schema updates. - Security: Since this skill interacts with your corporate data, ensure your MCP tokens have the minimum required permissions to perform intended tasks.
- Latency: Because the skill communicates via remote MCP servers, execution time may vary based on your internet connection and the responsiveness of the Lark API.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-al-one-mcp-lark": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
maishou
商品价格全网对比技能,获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券,当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.
qwen-asr
Transcribe audio files using Qwen ASR (千问STT). Use when the user sends voice messages and wants them converted to text.
edgeone
Deploy HTML content to EdgeOne Pages, return the public URL.
edge-tts-uvx
Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
mcp-hass
The skill for control Home Assistant smart home devices and query states using MCP protocol.