Catalysishub MCP Server

🚀 Catalysis Hub MCP Server

This server provides a Model Context Protocol (MCP) server interface by directly accessing the GraphQL API of Catalysis Hub. It enables programmatic access to catalysis research data and supports flexible GraphQL queries.

✨ Features

• Direct GraphQL Access: Execute any valid GraphQL query to access the Catalysis Hub API.
• Comprehensive Data Access:
  • Catalytic reactions (equations, conditions, catalysts)
  • Material systems (structures, properties, descriptors)
  • Research publications (titles, DOIs, authors)
  • Surface reaction data (adsorption energies, binding sites)
• MCP Standard Compatibility: Implement the Model Context Protocol to support the interoperability of AI agents.
• Flexible Query Support: Support complex queries and variable parameterization.
• Error Handling: Provide robust error reporting covering API connection and query execution.

🔧 Technical Details

• Server Configuration (consistent with claude_desktop_config.json):

  {
    "command": "/Users/quentincody/.env/bin/python3",
    "args": ["/Users/quentincody/catalysishub-mcp-server/catalysishub_mcp_server.py"],
    "options": {
      "cwd": "/Users/quentincody/catalysishub-mcp-server"
    }
  }
  

• Core Dependencies: Use httpx for asynchronous HTTP requests.
• Transport Layer: Follow the input-output communication of the MCP specification.

📦 Installation

1. Clone the repository:

   git clone <repository_url>
   cd catalysishub-mcp-server
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Verify the installation:

   python3 catalysishub_mcp_server.py --version
   # The output should be: catalysishub-mcp-server 0.1.0
   

💻 Usage Examples

Basic Usage

from mcp.client import MCPClient

async with MCPClient("catalysishub") as hub:
    result = await hub.catalysishub_graphql(
        query="""{
            reactions(first: 5) {
                edges {
                    node {
                        id
                        Equation
                        Temperature
                    }
                }
            }
        }"""
    )
    print(json.loads(result))

Advanced Usage

variables = {
    "materialId": "mp-1234",
    "firstResults": 5
}

response = await hub.catalysishub_graphql(
    query="""query GetMaterialById($materialId: String!, $firstResults: Int!) => Material {
        material(id: $materialId) {
            name
            properties(limit: $firstResults) {
                id
                value
            }
        }
    }""",
    variables=variables
)

Query Optimization

Pagination and Filtering

Use skip and limit for pagination or add filtering conditions:

{
  reactions(skip: 0, limit: 5, where: {property: "temperature"}) {
    edges {
      node {
        id
        Equation
        Temperature
      }
    }
  }
}

Handling Large Queries

For large-scale data, it is recommended to use batch processing:

from mcp.client import MCPClient

client = MCPClient("catalysishub")
batch_query = client.catalysishub_graphql(
    query=query,
    variables=variables
)
result = await batch_query()

Response Structure

Example of a successful response:

{
  "data": {
    "reactions": {
      "edges": [
        {
          "node": {
            "id": "123",
            "Equation": "E = mc^2",
            "Temperature": 500
          }
        },
        // Other nodes...
      ]
    }
  }
}

Example of an error response:

{
  "errors": [
    {
      "message": "Field 'reactions' not found in type 'Query'",
      "path": ["reactions"],
      "locations": [{ "line": 1, "column": 3 }]
    }
  ]
}

Troubleshooting

Common Issues

• Error: Field not found

  • Check the field names in the query for accuracy.
  • Ensure that the GraphQL schema used is consistent with the server.

• Performance issues

  • Use pagination and filtering to limit the data volume.
  • Avoid requesting a large amount of data at once.

Contact Support

For further assistance, please contact:

• Email: support@catalsishub.com
• Phone: +1 (555) 123-4567

📚 Documentation

• GraphQL Protocol
• MCP Specification
• Python Asynchronous Programming

With the above information, you can fully understand and utilize the various functions of the Catalysis Hub MCP Server.