
mcp adapter service
一个轻量级容器化的FastAPI服务,用于接收MCP请求并异步分发到后端服务。
Repository Info
About This Server
一个轻量级容器化的FastAPI服务,用于接收MCP请求并异步分发到后端服务。
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
MCP Adapter Service
A lightweight, containerized FastAPI service that receives Model Context Protocol (MCP) requests and asynchronously dispatches them to backend services such as:
maceopt: Geometry optimization using MACEzeopp: Structural analysis using Zeo++xtb: GFN1-xTB-based optimization
🚀 Features
- ✅ Supports standardized MCP request format
- 🧠 Asynchronous task queue via Celery
- 🧪 Rich structured logging with trace ID
- 🔌 Easily extendable to more backend models
- 🐳 Fully containerized for server deployment
- 🧵 Route-based Zeo++ multi-function support
📦 Deployment (Docker Compose)
1. Clone the repository
git clone https://github.com/your-org/mcp-adapter-service.git
cd mcp-adapter-service
```text
2. Configure environment
Create a .env file:
# Redis
REDIS_URL=redis://redis:6379/0
CELERY_BROKER_URL=redis://redis:6379/0
CELERY_RESULT_BACKEND=redis://redis:6379/0
# Backend services
MACEOPT_BASE_URL=http://192.168.100.208:4748
ZEO_BASE_URL=http://192.168.100.208:9876
XTB_BASE_URL=http://192.168.100.208:4548
3. Build and start all services
docker-compose up --build -d
Access the API via: http://<your-server-ip>:9000/docs
🧠 API Endpoints
POST /mcp
Submit a structured request to route to the appropriate backend.
Example body:
{
"input": "<.xyz or .cssr content>",
"context": {
"task_id": "mcp_001",
"model": "zeopp",
"parameters": {
"route": "surface_area",
"output_filename": "output.sa"
}
}
}
GET /result/{task_id}
Query asynchronous task result by task ID.
GET /zeopp/list_routes
List all supported Zeo++ analysis endpoints.
📂 Project Structure
app/
├── adapters/ # Dispatcher and router
├── middleware/ # Trace logging
├── models/ # Pydantic schema
├── services/ # Celery tasks and backend clients
├── utils/ # Rich logger and trace ID
├── main.py # FastAPI app entry
celery_worker.py # Celery worker entry
Dockerfile
docker-compose.yml
.env.template
👤 Author
Shibo Li · 2025
MIT License
Quick Start
Clone the repository
git clone https://github.com/lichman0405/mcp-adapter-serviceInstall dependencies
cd mcp-adapter-service
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.