Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Unofficial MCP server for searching and retrieving scientific data from the Catalysis Hub database, providing access to computational catalysis research and surface reaction data.

README.md

Catalysis Hub MCP Server

A Model Context Protocol (MCP) server interface to Catalysis Hub's GraphQL API, enabling programmatic access to catalysis research data through flexible GraphQL queries.

Key Features

  • Direct GraphQL Access: Execute any valid GraphQL query against Catalysis Hub's 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 Compliance: Implements the Model Context Protocol for AI-agent interoperability
  • Flexible Query Support: Execute complex queries with variables parameterization
  • Error Handling: Robust error reporting for API connectivity and query execution

License and Citation

This project is available under the MIT License with an Academic Citation Requirement. This means you can freely use, modify, and distribute the code, but any academic or scientific publication that uses this software must provide appropriate attribution.

For academic/research use:

If you use this software in a research project that leads to a publication, presentation, or report, you must cite this work according to the format provided in CITATION.md.

For commercial/non-academic use:

Commercial and non-academic use follows the standard MIT License terms without the citation requirement.

By using this software, you agree to these terms. See LICENSE.md for the complete license text.

Implementation Details

  • Server Configuration (matches 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 Dependency: httpx for asynchronous HTTP requests
  • Transport: Standard input/output communication following MCP specifications

Setup & Installation

  1. Clone the repository:
   git clone <repository_url>
   cd catalysishub-mcp-server
  1. Install dependencies:
   pip install -r requirements.txt
  1. Verify installation:
   python3 catalysishub_mcp_server.py --version
   # Should output: catalysishub-mcp-server 0.1.0

Usage Examples

Basic Query Execution

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))

Parameterized Query with Variables

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

response = await hub.catalysishub_graphql(
    query="""query GetMaterial($materialId: String!, $firstResults: Int!) {
        systems(uniqueId: $materialId) {
            edges {
                node {
                    energy
                    Cifdata
                    relatedReactions(first: $firstResults) {
                        edges {
                            node {
                                id
                                Equation
                            }
                        }
                    }
                }
            }
        }
    }""",
    variables=variables
)

Query Optimization Tips

  1. Use GraphQL Fragments:
   fragment ReactionDetails on Reaction {
       id
       Equation
       ActivationEnergy
       Catalyst {
           formula
           surface
       }
   }
   
   query {
       reactions(first: 10) {
           edges {
               node {
                   ...ReactionDetails
               }
           }
       }
   }
  1. Batch Related Queries:
   query BatchQuery {
       reactions: reactions(first: 5) { edges { node { id Equation } } }
       materials: systems(first: 5) { edges { node { formula energy } } }
   }

Response Structure

Successful responses follow this structure: ``json { "data": { / Query results / }, "extensions": { "responseMetadata": { "requestDuration": 145, "apiVersion": "2024-06" } } } ``

Error responses include detailed diagnostics: ``json { "errors": [{ "message": "Cannot query field 'invalidField' on type 'Reaction'", "locations": [{"line": 5, "column": 21}], "path": ["query", "reactions", "edges", "node", "invalidField"] }] } ``

Troubleshooting

Common Issues:

  • HTTP Request Error: Verify network connectivity to api.catalysis-hub.org
  • JSON Decode Error: Check query syntax using Catalysis Hub's GraphQL Playground
  • Timeout Errors: Add timeout parameter to complex queries

Acknowledgements

This project builds on the Model Context Protocol (MCP) framework and is designed to interface with the Catalysis Hub database, a comprehensive resource for catalysis research data.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Databases servers.