larks-mcp
Enables fetching document content from Lark Suite using OAuth authentication, with support for streamable HTTP transport and Docker deployment.
README
Larks MCP Server - Python Implementation
Python implementation of the Larks MCP server using FastMCP, converted from Node.js/TypeScript.
Installation
cd python
pip install -r requirements.txt
Running the Server
Option 1: Using Docker Compose (Recommended)
# Copy .env.example to .env and fill in your credentials
cp .env.example .env
# Edit .env with your credentials
# Build and start the container
docker compose up -d
# View logs
docker compose logs -f
# Stop the container
docker compose down
Option 2: Using .env file (Local)
# Copy .env.example to .env and fill in your credentials
cp .env.example .env
# Edit .env with your credentials
# Run the server
python server.py
Option 3: Using environment variables
# Set environment variables
export LARKS_CLIENT_ID=your_client_id
export LARKS_CLIENT_SECRET=your_client_secret
export MCP_PORT=48080
# Run the server
python server.py
Note: Environment variables take precedence over .env file values.
Configuration
The server loads configuration from .env file and environment variables (env vars take precedence):
LARKS_CLIENT_ID: OAuth app ID (required)LARKS_CLIENT_SECRET: OAuth app secret (required)LARKS_REDIRECT_URI: OAuth redirect URI (default:http://localhost:48080/oauth/callback)LARKS_BEARER_TOKEN: Direct bearer token (optional, fallback if OAuth not used)LARKS_DOMAIN: OAuth domain (default:https://open.larksuite.com)LARKS_API_DOMAIN: API domain (default:https://open.larksuite.com)MCP_PORT: Server port (default:48080)MCP_HOST: Server host (default:0.0.0.0)
Cursor MCP Configuration
Use streamable HTTP transport:
{
"mcpServers": {
"larks-docs": {
"transport": "streamableHttp",
"url": "http://localhost:48080/mcp"
}
}
}
Start the server separately:
python server.py
Docker
Building the Image
docker build -t larks-mcp-python .
Running with Docker Compose
# Start the service
docker compose up -d
# View logs
docker compose logs -f larks-mcp-python
# Stop the service
docker compose down
Environment Variables in Docker
You can provide environment variables in several ways:
-
Via docker-compose.yml (recommended for Docker):
environment: - LARKS_CLIENT_ID=your_client_id - LARKS_CLIENT_SECRET=your_client_secret -
Via .env file (mounted as volume):
volumes: - ./.env:/app/.env:ro -
Via host environment variables:
export LARKS_CLIENT_ID=your_client_id export LARKS_CLIENT_SECRET=your_client_secret docker compose up -d
Features
- ✅ Streamable HTTP transport (plain HTTP POST, no SSE)
- ✅ OAuth authentication flow
- ✅ Document content fetching
- ✅ Same API as Node.js version
- ✅ Environment variable and .env file configuration
- ✅ Automatic token refresh handling
- ✅ Docker support with docker-compose
Differences from Node.js Version
- Uses FastMCP for easier server setup
- Async/await pattern throughout
- Python-native HTTP client (httpx)
- Same functionality, cleaner Python code
- Uses python-dotenv for .env file support
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。