Catalysis Hub MCP Server

What is Catalysis Hub MCP Server?

A Model Context Protocol (MCP) server that provides a programmatic interface to Catalysis Hub’s GraphQL API, enabling AI agents to query catalysis research data such as reactions, materials, publications, and surface data. It is designed for researchers and developers who need flexible, machine-readable access to the Catalysis Hub database.

How to use Catalysis Hub MCP Server?

Clone the repository, install dependencies with pip install -r requirements.txt, and verify with python3 catalysishub_mcp_server.py --version. Use an MCP client (e.g., MCPClient) to call the catalysishub_graphql tool, passing a GraphQL query string and optional variables. The server communicates via standard input/output and is configured in claude_desktop_config.json with the Python interpreter path and script path.

Key features of Catalysis Hub MCP Server

• Direct execution of any valid GraphQL query against Catalysis Hub’s API.
• Access to catalytic reactions, materials, publications, and surface data.
• MCP standard compliance for AI-agent interoperability.
• Supports parameterized queries with variable binding.
• Robust error handling for connectivity and query issues.
• Academic citation requirement under MIT License.

Use cases of Catalysis Hub MCP Server

• Retrieve catalytic reactions with specific conditions (temperature, catalyst).
• Query material systems by unique ID and fetch structural data (CIF, energy).
• Search research publications by DOI, title, or author.
• Batch related queries (reactions and materials) in a single request.
• Integrate catalysis data into automated research workflows or AI assistants.

FAQ from Catalysis Hub MCP Server

What kind of data can I query?

You can query catalytic reactions (equations, conditions, catalysts), material systems (structures, properties, descriptors), research publications (titles, DOIs, authors), and surface reaction data (adsorption energies, binding sites).

How do I install and set up the server?

Clone the repository, install dependencies from requirements.txt, and verify the version. The server is started by running catalysishub_mcp_server.py with Python; a sample claude_desktop_config.json configuration is provided.

What are the core dependencies?

The main dependency is httpx for asynchronous HTTP requests. The server uses standard input/output for MCP transport and requires a Python environment.

How are errors handled?

The server reports detailed error messages for API connectivity failures, JSON decode issues (invalid GraphQL syntax), and timeout errors. Users are directed to Catalysis Hub’s GraphQL Playground for query validation.

What is the license and citation requirement?

The project is MIT Licensed with an Academic Citation Requirement. Academic publications must cite the software as specified in CITATION.md; commercial/non-academic use follows standard MIT terms.