PubChem MCP Server logo

PubChem MCP Server

by PhelanShao

The PubChem MCP Server is a Python implementation of a Model Context Protocol (MCP) server designed to retrieve chemical compound data from the PubChem database. It provides easy access to compound properties, 2D structures, and 3D molecular coordinates through a standard MCP interface.

View on GitHub

Last updated: N/A

What is PubChem MCP Server?

The PubChem MCP Server is a Python-based server that allows AI models to query chemical compound information from the PubChem database using the Model Context Protocol (MCP).

How to use PubChem MCP Server?

To use the server, you need to install it from source using pip. Then, configure your MCP configuration file to point to the server's mcp_server.py script. You can then use the available tools, get_pubchem_data and download_structure, by sending MCP requests with appropriate parameters like compound name/CID and desired output format.

Key features of PubChem MCP Server

  • Query compounds by name or PubChem CID

  • Retrieve comprehensive compound data (IUPAC name, molecular formula, weight, SMILES, InChI)

  • Support for JSON, CSV, and XYZ output formats

  • Built-in caching system for improved performance

  • Automatic retry mechanism for API reliability

  • Fallback 3D structure generation if PubChem 3D is unavailable

Use cases of PubChem MCP Server

  • Enabling AI models to understand and reason about chemical compounds

  • Integrating chemical data into AI-driven drug discovery pipelines

  • Providing AI models with access to chemical structures for property prediction

  • Using AI models to generate chemical structures based on desired properties

FAQ from PubChem MCP Server

What is MCP?

MCP stands for Model Context Protocol, a standard for AI models to interact with external tools and servers.

What is PubChem?

PubChem is a public database of chemical molecules and their activities against biological assays.

How do I install the server?

Clone the repository, navigate to the python_version directory, and run pip install -e .

How do I configure the server for use with Claude?

Add the provided JSON snippet to your MCP configuration file, adjusting the path to mcp_server.py as needed.

What output formats are supported?

The server supports JSON, CSV, and XYZ output formats.