catalysishub-mcp-server

catalysishub-mcp-server is an MCP (Model Context Protocol) server that serves as an interface to the Catalysis Hub GraphQL API, providing programmatic access to catalysis research data. It allows AI agents to interact with the Catalysis Hub database using the standardized MCP protocol.

Purpose

The tool is designed to provide AI agents with programmatic access to catalysis research data in the Catalysis Hub database, supporting the execution of any valid GraphQL query.

Key Capabilities

• Direct GraphQL Access: Can execute any valid GraphQL query against the Catalysis Hub API.
• Comprehensive Data Access: Covers catalytic reactions (equations, conditions, catalysts), material systems (structures, properties, descriptors), research publications (titles, DOIs, authors), and surface reaction data (adsorption energies, binding sites).
• MCP Standard Compliance: Implements the Model Context Protocol, supporting AI agent interoperability.
• Flexible Query Support: Supports complex queries parameterized with variables.
• Error Handling: Provides robust error reporting for API connections and query execution.

Usage

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
   # 应输出：catalysishub-mcp-server 0.1.0
   

Server Configuration (matching 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"
  }
}

Query Examples

• Basic query execution
• Parameterized queries with variables
• Query optimization tips: use GraphQL fragments, batch related queries.

Applicable Scenarios

Suitable for academic or research scenarios that require programmatic access to catalysis research data, such as retrieving catalytic reactions, material properties, publications, and surface reaction data through AI agents.

Limitations

• This project is an unofficial interface and depends on the Catalysis Hub GraphQL API.
• Academic use requires citation as per CITATION.md; commercial/non-academic use follows the standard MIT license terms.
• The core dependency httpx is used for asynchronous HTTP requests; transport uses standard input/output communication.
• Common issues include HTTP request errors (check network connection), JSON decoding errors (check query syntax), and timeout errors (add a timeout parameter for complex queries).