feishu-cli-mcp
Exposes the official lark-cli as an MCP server, enabling agents to execute arbitrary CLI commands, query API schemas, and manage authentication.
README
feishu-cli-mcp
把官方 lark-cli 暴露成 MCP 服务,让 Agent 通过清晰的上下文协议使用飞书/ Lark CLI 的完整能力。
设计
本项目不重写飞书 API,也不手工封装 200+ CLI 命令。MCP 只做一层受控代理:
lark_cli_run:执行任意lark-cli参数数组,覆盖 CLI 全部能力。lark_cli_schema:查询 API 方法参数、响应、身份和 scopes。lark_cli_help:查询服务或命令帮助,发现快捷命令。lark_cli_auth_status:检查登录、scope 和身份状态。
Agent 上下文通过 MCP Resources / Prompts 暴露:
lark://agent-guide:Agent 使用规则。lark://command-model:快捷命令、API 命令、Raw API 的选择顺序。lark://skills:官方 CLI 覆盖的业务域。lark://security:写操作、scope、Docker 和 HTTP 安全规则。lark://schema/{method}:动态读取某个 API 方法 schema。lark_plan_command:让 Agent 先规划命令。lark_safe_write:让 Agent 走 schema、dry-run、用户确认流程。
Agent 协议
Agent 必须按这个顺序使用:
- 读
lark://agent-guide和lark://command-model。 - 优先查
lark_cli_help,选择+shortcut。 - 快捷命令不够时,用
lark_cli_schema查 API 命令。 - API 命令不够时,才用
lark_cli_run调 rawapi METHOD /open-apis/...。 - 读操作用
intent=read。 - 写操作用
intent=write,先 help/schema,能 dry-run 就先 dry-run。 intent=write或intent=auth_config必须传confirm=true,否则服务拒绝执行。- 机器读取优先加
--format json。
示例:
{
"tool": "lark_cli_run",
"arguments": {
"args": ["calendar", "+agenda", "--format", "json"],
"intent": "read"
}
}
写操作示例:
{
"tool": "lark_cli_run",
"arguments": {
"args": ["im", "+messages-send", "--chat-id", "oc_xxx", "--text", "hello", "--dry-run"],
"intent": "write",
"confirm": true
}
}
本地运行
npm install
npm run build
node dist/index.js --transport stdio
HTTP:
copy .env.example .env
npm run build
node dist/index.js --transport http
MCP URL:
http://127.0.0.1:3333/mcp
如果设置了 MCP_HTTP_TOKEN,客户端需要传:
Authorization: Bearer <token>
Docker / Unraid
cp .env.example .env
docker compose up -d --build
Unraid 模板关键配置:
- Repository/Image:
feishu-cli-mcp:latest或你的 GitHub 镜像地址 - WebUI / MCP URL:
http://<unraid-ip>:3333/mcp - Port:
3333:3333 - Volume:
/mnt/user/appdata/feishu-cli-mcp/lark-cli:/data/lark-cli - Env:
MCP_TRANSPORT=httpMCP_HOST=0.0.0.0MCP_PORT=3333MCP_HTTP_TOKEN=<强随机 token>LARK_CLI_HOME=/data/lark-cli
持久化点是 /data/lark-cli。这里保存 CLI 配置和授权状态。
初始化飞书授权
容器启动后,通过 MCP 执行:
{
"tool": "lark_cli_run",
"arguments": {
"args": ["config", "init", "--new"],
"intent": "auth_config",
"confirm": true
}
}
然后登录:
{
"tool": "lark_cli_run",
"arguments": {
"args": ["auth", "login", "--recommend", "--no-wait"],
"intent": "auth_config",
"confirm": true
}
}
把 CLI 输出里的授权 URL 发给用户完成浏览器授权。
验证
npm run check
docker compose up -d --build
curl http://127.0.0.1:3333/healthz
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.