Skip to main content
Glama
Augmented-Nature

Unofficial PubChem MCP Server

search_compounds

Search PubChem database for chemical compounds using names, CAS numbers, formulas, or identifiers to retrieve molecular data and properties.

Instructions

Search PubChem database for compounds by name, CAS number, formula, or identifier

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query (compound name, CAS, formula, or identifier)
search_typeNoType of search to perform (default: name)
max_recordsNoMaximum number of results (1-10000, default: 100)

Implementation Reference

  • The main handler function that executes the search_compounds tool. Validates args, performs PubChem PUG API search by specified type (default 'name'), retrieves CIDs, fetches details for top 10 (formula, weight, SMILES, IUPAC), returns formatted JSON response or no-results message.
    private async handleSearchCompounds(args: any) {
      if (!isValidCompoundSearchArgs(args)) {
        throw new McpError(ErrorCode.InvalidParams, 'Invalid compound search arguments');
      }
    
      try {
        const searchType = args.search_type || 'name';
        const maxRecords = args.max_records || 100;
    
        const response = await this.apiClient.get(`/compound/${searchType}/${encodeURIComponent(args.query)}/cids/JSON`, {
          params: {
            MaxRecords: maxRecords,
          },
        });
    
        if (response.data?.IdentifierList?.CID?.length > 0) {
          const cids = response.data.IdentifierList.CID.slice(0, 10);
          const detailsResponse = await this.apiClient.get(`/compound/cid/${cids.join(',')}/property/MolecularFormula,MolecularWeight,CanonicalSMILES,IUPACName/JSON`);
    
          return {
            content: [
              {
                type: 'text',
                text: JSON.stringify({
                  query: args.query,
                  search_type: searchType,
                  total_found: response.data.IdentifierList.CID.length,
                  details: detailsResponse.data,
                }, null, 2),
              },
            ],
          };
        }
    
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify({ message: 'No compounds found', query: args.query }, null, 2),
            },
          ],
        };
      } catch (error) {
        throw new McpError(
          ErrorCode.InternalError,
          `Failed to search compounds: ${error instanceof Error ? error.message : 'Unknown error'}`
        );
      }
    }
  • src/index.ts:371-382 (registration)
    Tool registration in the MCP server's ListToolsRequestSchema handler, defining the name, description, and input schema for search_compounds.
      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'],
      },
    },
  • JSON schema defining the input parameters for the search_compounds tool: required 'query' string, optional 'search_type' enum, and 'max_records' number.
    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'],
    },
  • Type guard and validation function for search_compounds input arguments, ensuring query is non-empty string, search_type is valid enum or undefined, max_records is positive number <=10000 or undefined.
    const isValidCompoundSearchArgs = (
      args: any
    ): args is { query: string; search_type?: string; max_records?: number } => {
      return (
        typeof args === 'object' &&
        args !== null &&
        typeof args.query === 'string' &&
        args.query.length > 0 &&
        (args.search_type === undefined || ['name', 'smiles', 'inchi', 'sdf', 'cid', 'formula'].includes(args.search_type)) &&
        (args.max_records === undefined || (typeof args.max_records === 'number' && args.max_records > 0 && args.max_records <= 10000))
      );
    };
  • src/index.ts:740-741 (registration)
    Dispatch case in the CallToolRequestSchema switch statement that routes 'search_compounds' calls to the handleSearchCompounds method.
    case 'search_compounds':
      return await this.handleSearchCompounds(args);
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions the search functionality but doesn't disclose behavioral traits such as rate limits, authentication needs, response format, pagination, or error handling, which are critical for a search tool with no structured safety hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's appropriately sized and front-loaded, clearly stating the tool's purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a search tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects, response format, and usage context, making it inadequate for guiding an AI agent effectively in this rich sibling environment.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value by listing search types ('name, CAS number, formula, or identifier'), which partially overlaps with the 'search_type' enum, but doesn't provide additional syntax or format details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Search PubChem database') and resource ('compounds'), specifying what the tool does. It distinguishes from siblings like 'search_by_cas_number' or 'search_by_smiles' by mentioning multiple search types, though it doesn't explicitly contrast with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. With many sibling tools like 'search_by_cas_number' or 'search_similar_compounds', the description lacks explicit when/when-not instructions or named alternatives, leaving usage context unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Augmented-Nature/Augmented-Nature-PubChem-MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server