PubChem Data Acquisition Utility

This utility component facilitates the acquisition of core molecular properties for specified compounds utilizing the PubChem RESTful API endpoint.

Prerequisites

• Runtime Environment: Python version 3.10 or higher
• Dependency Packages:
  • python-dotenv
  • requests (for HTTP communications)
  • mcp (Core framework dependency)
  • uvicorn (For potential serving infrastructure)

Setup Procedure

Local Dependency Installation:

• Execute installation directly from the source repository clone location:

bash git clone [project repository URL] cd [project directory] pip install .

Service Configuration (for MCP framework integration):

The servers_config.json file adheres to the configuration schema employed by Claude Desktop, enabling seamless integration across multiple defined network endpoints.

Example configuration snippet:

{ "mcpServers": { "pubchem_access": { "command": "uvx", "args": ["pubchem_data_extractor"] } } }

Illustrative Output Structure

When successfully executed against a compound record (e.g., Aspirin), the resulting data object will resemble this schema:

{ "Drug Name": "Aspirin", "CAS Number": "50-78-2", "Molecular Weight": 180.16, "Molecular Formula": "C9H8O4", "SMILES": "CC(=O)OC1=CC=CC=C1C(=O)O", "Synonyms": [ "2-(Acetyloxy)benzoic Acid", "Acetylsalicylic Acid", "Acetysal", "Acylpyrin", "Aloxiprimum", "Aspirin", "Colfarit", "Dispril", "Easprin" ], "InchI Key": "BSYNRYMUTXBXSQ-UHFFFAOYSA-N", "IUPAC Name": "2-acetyloxybenzoic acid", "ATC Code": "N02BA01", "Details Link": "https://pubchem.ncbi.nlm.nih.gov/compound/2244" }