PubChem MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_compoundsC | Search PubChem database for compounds by name, CAS number, formula, or identifier |
| get_compound_infoC | Get detailed information for a specific compound by PubChem CID |
| search_by_smilesC | Search for compounds by SMILES string (exact match) |
| search_by_inchiB | Search for compounds by InChI or InChI key |
| search_by_cas_numberC | Search for compounds by CAS Registry Number |
| get_compound_synonymsB | Get all names and synonyms for a compound |
| search_similar_compoundsC | Find chemically similar compounds using Tanimoto similarity |
| substructure_searchB | Find compounds containing a specific substructure |
| superstructure_searchC | Find larger compounds that contain the query structure |
| get_3d_conformersC | Get 3D conformer data and structural information |
| analyze_stereochemistryC | Analyze stereochemistry, chirality, and isomer information |
| get_compound_propertiesC | Get molecular properties (MW, logP, TPSA, etc.) |
| calculate_descriptorsC | Calculate comprehensive molecular descriptors and fingerprints |
| predict_admet_propertiesC | Predict ADMET properties (Absorption, Distribution, Metabolism, Excretion, Toxicity) |
| assess_drug_likenessC | Assess drug-likeness using Lipinski Rule of Five, Veber rules, and PAINS filters |
| analyze_molecular_complexityC | Analyze molecular complexity and synthetic accessibility |
| get_pharmacophore_featuresC | Get pharmacophore features and binding site information |
| search_bioassaysC | Search for biological assays by target, description, or source |
| get_assay_infoC | Get detailed information for a specific bioassay by AID |
| get_compound_bioactivitiesC | Get all bioassay results and activities for a compound |
| search_by_targetC | Find compounds tested against a specific biological target |
| compare_activity_profilesC | Compare bioactivity profiles across multiple compounds |
| get_safety_dataC | Get GHS hazard classifications and safety information |
| get_toxicity_infoB | Get toxicity data including LD50, carcinogenicity, and mutagenicity |
| assess_environmental_fateC | Assess environmental fate including biodegradation and bioaccumulation |
| get_regulatory_infoC | Get regulatory information from FDA, EPA, and international agencies |
| get_external_referencesC | Get links to external databases (ChEMBL, DrugBank, KEGG, etc.) |
| search_patentsC | Search for chemical patents and intellectual property information |
| get_literature_referencesC | Get PubMed citations and scientific literature references |
| batch_compound_lookupC | Process multiple compound IDs efficiently |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 30 tools
Most tools have distinct purposes with clear boundaries, such as 'get_compound_info' for general data versus 'get_compound_properties' for molecular metrics. However, some overlap exists, like 'search_by_smiles' and 'substructure_search' both involving SMILES queries, which could cause minor confusion without careful reading of descriptions.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'analyze_molecular_complexity', 'calculate_descriptors', and 'search_compounds'. This uniformity makes the set predictable and easy to navigate, with no deviations in style or structure.
With 30 tools, the count is borderline high for a PubChem server, as it might overwhelm agents with many specialized functions. While it covers extensive chemical data needs, a more focused set of 15-25 tools could improve usability without sacrificing core functionality.
The tool set provides comprehensive coverage for chemical data retrieval and analysis, including search, retrieval, analysis, and prediction tools. It supports full CRUD-like workflows for compounds, assays, and properties, with no obvious gaps that would hinder agent operations in this domain.