PubChem MCP Server

Instructions

Implementation Reference

• src/index.ts:954-956 (handler)

  The main handler function for the 'search_by_cas_number' tool. It currently returns a placeholder response indicating that CAS search is not yet implemented.
  private async handleSearchByCasNumber(args: any) { return { content: [{ type: 'text', text: JSON.stringify({ message: 'CAS search not yet implemented', args }, null, 2) }] }; }
• src/index.ts:417-427 (schema)

  The input schema definition for the 'search_by_cas_number' tool, specifying that it requires a 'cas_number' string parameter.
  { name: 'search_by_cas_number', description: 'Search for compounds by CAS Registry Number', inputSchema: { type: 'object', properties: { cas_number: { type: 'string', description: 'CAS Registry Number (e.g., 50-78-2)' }, }, required: ['cas_number'], }, },
• src/index.ts:748-749 (registration)

  The switch case in the CallToolRequestSchema handler that dispatches to the tool's handler function.
  case 'search_by_cas_number': return await this.handleSearchByCasNumber(args);
• src/index.ts:366-733 (registration)

  The ListToolsRequestSchema handler that registers/declares the 'search_by_cas_number' tool among others, including its schema.
  private setupToolHandlers() { this.server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: [ // Chemical Search & Retrieval (6 tools) { name: 'search_compounds', description: 'Search PubChem database for compounds by name, CAS number, formula, or identifier', inputSchema: { type: 'object', properties: { query: { type: 'string', description: 'Search query (compound name, CAS, formula, or identifier)' }, search_type: { type: 'string', enum: ['name', 'smiles', 'inchi', 'sdf', 'cid', 'formula'], description: 'Type of search to perform (default: name)' }, max_records: { type: 'number', description: 'Maximum number of results (1-10000, default: 100)', minimum: 1, maximum: 10000 }, }, required: ['query'], }, }, { name: 'get_compound_info', description: 'Get detailed information for a specific compound by PubChem CID', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, format: { type: 'string', enum: ['json', 'sdf', 'xml', 'asnt', 'asnb'], description: 'Output format (default: json)' }, }, required: ['cid'], }, }, { name: 'search_by_smiles', description: 'Search for compounds by SMILES string (exact match)', inputSchema: { type: 'object', properties: { smiles: { type: 'string', description: 'SMILES string of the query molecule' }, }, required: ['smiles'], }, }, { name: 'search_by_inchi', description: 'Search for compounds by InChI or InChI key', inputSchema: { type: 'object', properties: { inchi: { type: 'string', description: 'InChI string or InChI key' }, }, required: ['inchi'], }, }, { name: 'search_by_cas_number', description: 'Search for compounds by CAS Registry Number', inputSchema: { type: 'object', properties: { cas_number: { type: 'string', description: 'CAS Registry Number (e.g., 50-78-2)' }, }, required: ['cas_number'], }, }, { name: 'get_compound_synonyms', description: 'Get all names and synonyms for a compound', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, // Structure Analysis & Similarity (5 tools) { name: 'search_similar_compounds', description: 'Find chemically similar compounds using Tanimoto similarity', inputSchema: { type: 'object', properties: { smiles: { type: 'string', description: 'SMILES string of the query molecule' }, threshold: { type: 'number', description: 'Similarity threshold (0-100, default: 90)', minimum: 0, maximum: 100 }, max_records: { type: 'number', description: 'Maximum number of results (1-10000, default: 100)', minimum: 1, maximum: 10000 }, }, required: ['smiles'], }, }, { name: 'substructure_search', description: 'Find compounds containing a specific substructure', inputSchema: { type: 'object', properties: { smiles: { type: 'string', description: 'SMILES string of the substructure query' }, max_records: { type: 'number', description: 'Maximum number of results (1-10000, default: 100)', minimum: 1, maximum: 10000 }, }, required: ['smiles'], }, }, { name: 'superstructure_search', description: 'Find larger compounds that contain the query structure', inputSchema: { type: 'object', properties: { smiles: { type: 'string', description: 'SMILES string of the query structure' }, max_records: { type: 'number', description: 'Maximum number of results (1-10000, default: 100)', minimum: 1, maximum: 10000 }, }, required: ['smiles'], }, }, { name: 'get_3d_conformers', description: 'Get 3D conformer data and structural information', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, conformer_type: { type: 'string', enum: ['3d', '2d'], description: 'Type of conformer data (default: 3d)' }, }, required: ['cid'], }, }, { name: 'analyze_stereochemistry', description: 'Analyze stereochemistry, chirality, and isomer information', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, // Chemical Properties & Descriptors (6 tools) { name: 'get_compound_properties', description: 'Get molecular properties (MW, logP, TPSA, etc.)', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, properties: { type: 'array', items: { type: 'string' }, description: 'Specific properties to retrieve (optional)' }, }, required: ['cid'], }, }, { name: 'calculate_descriptors', description: 'Calculate comprehensive molecular descriptors and fingerprints', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, descriptor_type: { type: 'string', enum: ['all', 'basic', 'topological', '3d'], description: 'Type of descriptors (default: all)' }, }, required: ['cid'], }, }, { name: 'predict_admet_properties', description: 'Predict ADMET properties (Absorption, Distribution, Metabolism, Excretion, Toxicity)', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, smiles: { type: 'string', description: 'SMILES string (alternative to CID)' }, }, required: [], }, }, { name: 'assess_drug_likeness', description: 'Assess drug-likeness using Lipinski Rule of Five, Veber rules, and PAINS filters', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, smiles: { type: 'string', description: 'SMILES string (alternative to CID)' }, }, required: [], }, }, { name: 'analyze_molecular_complexity', description: 'Analyze molecular complexity and synthetic accessibility', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'get_pharmacophore_features', description: 'Get pharmacophore features and binding site information', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, // Bioassay & Activity Data (5 tools) { name: 'search_bioassays', description: 'Search for biological assays by target, description, or source', inputSchema: { type: 'object', properties: { query: { type: 'string', description: 'General search query' }, target: { type: 'string', description: 'Target protein or gene name' }, source: { type: 'string', description: 'Data source (e.g., ChEMBL, NCGC)' }, max_records: { type: 'number', description: 'Maximum number of results (1-1000, default: 100)', minimum: 1, maximum: 1000 }, }, required: [], }, }, { name: 'get_assay_info', description: 'Get detailed information for a specific bioassay by AID', inputSchema: { type: 'object', properties: { aid: { type: 'number', description: 'PubChem Assay ID (AID)' }, }, required: ['aid'], }, }, { name: 'get_compound_bioactivities', description: 'Get all bioassay results and activities for a compound', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, activity_outcome: { type: 'string', enum: ['active', 'inactive', 'inconclusive', 'all'], description: 'Filter by activity outcome (default: all)' }, }, required: ['cid'], }, }, { name: 'search_by_target', description: 'Find compounds tested against a specific biological target', inputSchema: { type: 'object', properties: { target: { type: 'string', description: 'Target name (gene, protein, or pathway)' }, activity_type: { type: 'string', description: 'Type of activity (e.g., IC50, EC50, Ki)' }, max_records: { type: 'number', description: 'Maximum number of results (1-1000, default: 100)', minimum: 1, maximum: 1000 }, }, required: ['target'], }, }, { name: 'compare_activity_profiles', description: 'Compare bioactivity profiles across multiple compounds', inputSchema: { type: 'object', properties: { cids: { type: 'array', items: { type: 'number' }, description: 'Array of PubChem CIDs (2-50)', minItems: 2, maxItems: 50 }, activity_type: { type: 'string', description: 'Specific activity type for comparison (optional)' }, }, required: ['cids'], }, }, // Safety & Toxicity (4 tools) { name: 'get_safety_data', description: 'Get GHS hazard classifications and safety information', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'get_toxicity_info', description: 'Get toxicity data including LD50, carcinogenicity, and mutagenicity', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'assess_environmental_fate', description: 'Assess environmental fate including biodegradation and bioaccumulation', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'get_regulatory_info', description: 'Get regulatory information from FDA, EPA, and international agencies', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, // Cross-References & Integration (4 tools) { name: 'get_external_references', description: 'Get links to external databases (ChEMBL, DrugBank, KEGG, etc.)', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'search_patents', description: 'Search for chemical patents and intellectual property information', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, query: { type: 'string', description: 'Patent search query (alternative to CID)' }, }, required: [], }, }, { name: 'get_literature_references', description: 'Get PubMed citations and scientific literature references', inputSchema: { type: 'object', properties: { cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' }, }, required: ['cid'], }, }, { name: 'batch_compound_lookup', description: 'Process multiple compound IDs efficiently', inputSchema: { type: 'object', properties: { cids: { type: 'array', items: { type: 'number' }, description: 'Array of PubChem CIDs (1-200)', minItems: 1, maxItems: 200 }, operation: { type: 'string', enum: ['property', 'synonyms', 'classification', 'description'], description: 'Operation to perform (default: property)' }, }, required: ['cids'], }, }, ], }));