Catalysis Hub

MCP server exposing Catalysis Hub GraphQL data for AI agents to query reactions, materials, publications, and surface data.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can run the Catalysis Hub MCP Server to access catalysis data programmatically through GraphQL, enabling AI agents and automation to query reactions, materials, publications, and surface data with flexible parameterized requests.

How to use

You connect to the Catalysis Hub MCP Server through an MCP client and call the server’s GraphQL interface to retrieve data. Use the dedicated tool exposed by the server to execute GraphQL queries, optionally with variables, and receive structured results that you can feed into downstream analysis or agent workflows.

How to install

Prerequisites: ensure Python is installed on your system. You will use a Python-based MCP server entry point.

Clone the project directory that contains the MCP server code.
Install Python dependencies.
Start the MCP server and verify it reports its version.
Confirm the server is reachable and ready to accept queries from your MCP client.

Exact steps based on the server’s setup are shown below.

Configuration and run details

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

This configuration starts the MCP server as a local process. The server runs via a Python interpreter and executes the specified Python script. If your environment uses a different path to Python or the server script, adjust the command and arguments accordingly.

Usage with an MCP client

You interact with the server by calling the Catalysis Hub GraphQL endpoint through an MCP client. The client exposes a function named catalysishub_graphql to send a GraphQL query with optional variables.

Example usage in Python using an MCP client:

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))

You can also run parameterized queries by passing variables along with your query. This lets you request data for specific materials, systems, or counts without rewriting the query each time.

Notes on data and capabilities

The server provides access to catalytic reactions, material systems, publications, and surface reaction data through a flexible GraphQL interface. You can perform complex queries with variables and rely on robust error reporting for connectivity or query issues.

Troubleshooting

Common issues include network connectivity problems, JSON parsing errors from query responses, and timeouts on long-running queries. If you encounter these, verify network access to the server, validate your GraphQL query syntax, and consider adding timeout controls in your client.

Available tools

catalysishub_graphql

Executes GraphQL queries against the Catalysis Hub API with optional variables and returns structured results ready for consumption by MCP clients.