PubChem-MCP-Server and PDB-MCP-Server

PubChem-MCP-Server
45
Emerging
PDB-MCP-Server
38
Emerging
Maintenance 6/25
Adoption 7/25
Maturity 15/25
Community 17/25
Maintenance 6/25
Adoption 6/25
Maturity 9/25
Community 17/25
Stars: 34
Forks: 10
Downloads:
Commits (30d): 0
Language: JavaScript
License:
Stars: 21
Forks: 8
Downloads:
Commits (30d): 0
Language: JavaScript
License:
No Package No Dependents
No Package No Dependents

About PubChem-MCP-Server

Augmented-Nature/PubChem-MCP-Server

A comprehensive Model Context Protocol (MCP) server for accessing the PubChem chemical database. This server provides access to over 110 million chemical compounds with extensive molecular properties, bioassay data, and chemical informatics tools.

The server exposes 30+ tools across chemical search, structure analysis, molecular descriptors, bioassay data, and safety/toxicity information—accessible via MCP's standard protocol with URI-based resource templates like `pubchem://similarity/{smiles}`. Built in TypeScript with Axios, it implements PubChem's public REST API with built-in rate-limiting compliance (5 req/sec) and batch processing for up to 200 compounds, integrating seamlessly into drug discovery workflows alongside UniProt, ChEMBL, and AlphaFold MCP servers.

About PDB-MCP-Server

Augmented-Nature/PDB-MCP-Server

A Model Context Protocol (MCP) server that provides access to the Protein Data Bank (PDB) - the worldwide repository of information about the 3D structures of proteins, nucleic acids, and complex assemblies.

Exposes PDB search, structure retrieval, and quality validation through five core tools and URI-based resources, enabling direct access to multiple coordinate formats (PDB, mmCIF, mmTF, XML) and validation metrics like resolution, R-factors, and clash scores. Integrates with RCSB PDB's REST, Search, and File Download APIs via stdio transport for seamless integration with Claude Desktop and complementary servers like UniProt and AlphaFold MCP. Implements comprehensive error handling for API rate limiting, invalid identifiers, and network failures.

Scores updated daily from GitHub, PyPI, and npm data. How scores work