OpenAlex MCP Server

A production-ready Model Context Protocol (MCP) server that provides academic research tools using the OpenAlex API. Built with FastAPI and designed for deployment on Google Cloud Run.

Features

🔬 Academic Research Tools

• search_works - Search for papers, articles, and academic publications
• search_authors - Find researchers and their profiles with h-index, citations
• get_work_details - Get detailed metadata for specific papers
• search_concepts - Explore research topics and their relationships
• search_institutions - Find universities and research organizations
• get_citations - Analyze citation networks (citing/cited works)
• advanced_filter - Complex multi-criteria searches with OpenAlex filter syntax

🚀 MCP Protocol Features

• Streamable-HTTP transport - Modern HTTP/SSE-based communication
• JSON-RPC 2.0 - Standard message protocol
• Server-Sent Events - Real-time streaming for large responses
• Cloud-ready - Optimized for Google Cloud Run deployment

📊 OpenAlex Polite Access

• Automatic rate limiting (10 requests/second)
• Mailto parameter for polite pool access
• Proper User-Agent headers
• Exponential backoff for retries

Quick Start

Local Development

1. Clone and setup:

cd openalex-mcp-server
cp .env.example .env
# Edit .env and set your MAILTO_EMAIL

2. Install dependencies:

pip install -r requirements.txt

3. Run the server:

python server.py
# Or with uvicorn:
uvicorn server:app --reload --port 8080

4. Test the endpoint:

curl http://localhost:8080/health

Docker Local Testing

docker build -t openalex-mcp-server .
docker run -p 8080:8080 -e MAILTO_EMAIL=your-email@williamscollege.edu openalex-mcp-server

Google Cloud Run Deployment

Prerequisites

• Google Cloud SDK installed
• GCP project with Cloud Run API enabled
• Docker installed locally

Deployment Steps

1. Authenticate with Google Cloud:

gcloud auth login
gcloud config set project YOUR_PROJECT_ID

2. Build and push container:

# Configure Docker for Google Container Registry
gcloud auth configure-docker

# Build the image
docker build -t gcr.io/YOUR_PROJECT_ID/openalex-mcp-server .

# Push to Container Registry
docker push gcr.io/YOUR_PROJECT_ID/openalex-mcp-server

3. Deploy to Cloud Run:

gcloud run deploy openalex-mcp-server \
  --image gcr.io/YOUR_PROJECT_ID/openalex-mcp-server \
  --platform managed \
  --region us-central1 \
  --allow-unauthenticated \
  --set-env-vars MAILTO_EMAIL=your-email@williamscollege.edu \
  --memory 512Mi \
  --cpu 1 \
  --max-instances 10

4. Get your service URL:

gcloud run services describe openalex-mcp-server --platform managed --region us-central1 --format 'value(status.url)'

Alternative: One-Command Deployment

gcloud run deploy openalex-mcp-server \
  --source . \
  --region us-central1 \
  --allow-unauthenticated \
  --set-env-vars MAILTO_EMAIL=your-email@williamscollege.edu

MCP Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "openalex": {
      "transport": "streamable-http",
      "url": "https://YOUR-SERVICE-URL.run.app/mcp",
      "description": "OpenAlex academic research API"
    }
  }
}

Config file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

Other MCP Clients

The server implements standard MCP over HTTP/SSE, so it works with any compatible client:

import httpx
import json

# Initialize request
init_message = {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
        "protocolVersion": "2025-03-26",
        "clientInfo": {
            "name": "my-client",
            "version": "1.0.0"
        }
    }
}

response = httpx.post(
    "https://YOUR-SERVICE-URL.run.app/mcp",
    json=init_message,
    headers={"Content-Type": "application/json"}
)

print(response.json())

Usage Examples

Search for Papers

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "search_works",
    "arguments": {
      "query": "machine learning climate change",
      "publication_year": "2020-2024",
      "open_access": true,
      "limit": 10
    }
  }
}

Find Researchers

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search_authors",
    "arguments": {
      "name": "Andrew Ng",
      "institution": "Stanford",
      "limit": 5
    }
  }
}

Get Citation Network

{
  "jsonrpc": "2.0",
  "id": 4,
  "method": "tools/call",
  "params": {
    "name": "get_citations",
    "arguments": {
      "work_id": "W2741809807",
      "direction": "citing",
      "limit": 50
    }
  }
}

Advanced Filtering

{
  "jsonrpc": "2.0",
  "id": 5,
  "method": "tools/call",
  "params": {
    "name": "advanced_filter",
    "arguments": {
      "entity_type": "works",
      "filters": {
        "publication_year": ">2020",
        "cited_by_count": ">100",
        "is_oa": true
      },
      "search": "artificial intelligence",
      "sort": "cited_by_count:desc",
      "limit": 25
    }
  }
}

API Endpoints

POST /mcp

Main MCP endpoint for JSON-RPC messages. Supports both JSON and SSE responses.

Headers:

• Content-Type: application/json (required)
• Accept: application/json (JSON response) or Accept: text/event-stream (SSE)

GET /mcp

Optional SSE endpoint for server-initiated messages (keepalive, notifications).

Headers:

• Accept: text/event-stream (required)

GET /health

Health check endpoint for monitoring.

Response: {"status": "healthy", "service": "openalex-mcp-server", "version": "1.0.0"}

GET /

Service information and endpoint documentation.

Environment Variables

Variable	Default	Description
PORT	8080	Server port (Cloud Run sets automatically)
MAILTO_EMAIL	researcher@williamscollege.edu	Required for polite pool access
OPENALEX_BASE_URL	https://api.openalex.org	OpenAlex API endpoint
MAX_REQUESTS_PER_SECOND	10	Rate limit for API calls
LOG_LEVEL	INFO	Logging verbosity
ALLOWED_ORIGINS	None	CORS allowed origins (comma-separated)

Architecture

openalex-mcp-server/
├── server.py              # FastAPI app with HTTP/SSE transport
├── mcp_handler.py         # MCP protocol & JSON-RPC handling
├── config.py              # Environment configuration
├── tools/
│   ├── __init__.py
│   ├── search.py          # OpenAlex API tool implementations
│   ├── filters.py         # Filter utilities
│   └── utils.py           # Formatting helpers
├── Dockerfile             # Cloud Run deployment
├── requirements.txt       # Python dependencies
├── .env.example           # Environment template
├── claude_desktop_config.json  # Client config example
└── README.md

Development

Adding New Tools

1. Implement the tool function in tools/search.py:

async def my_new_tool(param1: str, param2: int = 10) -> str:
    """Tool description."""
    # Implementation
    return json.dumps(result)

2. Add to MCPHandler in mcp_handler.py:

self.tools = {
    # ... existing tools
    "my_new_tool": my_new_tool,
}

3. Add schema in _get_tool_schema():

schemas = {
    # ... existing schemas
    "my_new_tool": {
        "description": "Tool description",
        "inputSchema": {
            "type": "object",
            "properties": {
                "param1": {"type": "string", "description": "..."},
                "param2": {"type": "integer", "default": 10}
            },
            "required": ["param1"]
        }
    }
}

Running Tests

# Install test dependencies
pip install pytest pytest-asyncio httpx

# Run tests
pytest

Monitoring Cloud Run

# View logs
gcloud run services logs read openalex-mcp-server --region us-central1

# Check service status
gcloud run services describe openalex-mcp-server --region us-central1

Security Considerations

Current Configuration (Development)

• No authentication required
• CORS allows all origins
• Suitable for testing and internal use

Production Hardening

1. Enable authentication:

gcloud run deploy openalex-mcp-server \
  --no-allow-unauthenticated

2. Set allowed origins in .env:

ALLOWED_ORIGINS=https://yourdomain.com,https://anotherdomain.com

3. Use Cloud Run IAM for access control
4. Enable Cloud Armor for DDoS protection
5. Set up VPC for private networking

Rate Limiting & Polite Access

The server implements OpenAlex polite pool best practices:

• ✅ 10 requests/second rate limit (vs 6 req/s for non-polite)
• ✅ Mailto parameter in all requests
• ✅ User-Agent header with contact info
• ✅ Exponential backoff for errors
• ✅ Response caching (where appropriate)

Always set MAILTO_EMAIL to get better rate limits!

Troubleshooting

Issue: "Origin not allowed"

Solution: Set ALLOWED_ORIGINS environment variable or update CORS middleware in server.py

Issue: Rate limiting errors

Solution: Verify MAILTO_EMAIL is set correctly for polite pool access

Issue: Cloud Run timeout

Solution: Increase timeout in deployment:

gcloud run deploy openalex-mcp-server --timeout 300

Issue: Memory errors

Solution: Increase memory allocation:

gcloud run deploy openalex-mcp-server --memory 1Gi

Resources

• OpenAlex API Documentation
• Model Context Protocol Specification
• Google Cloud Run Documentation
• FastAPI Documentation

Contributing

Contributions welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Add tests for new functionality
4. Submit a pull request

License

MIT License - See LICENSE file for details

Support

For issues and questions:

• OpenAlex API: support@openalex.org
• Williams College: Contact your research computing support

---

Built for Williams College undergraduate researchers 🎓

Happy researching! 🔬