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
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.