Skip to main content
Glama
Open Drug Data MCP
by knorby

Search ingredients across open drug and cosmetic data sources

drugdata_search_ingredients
Read-onlyIdempotent

Search ingredients across openFDA, CosIng, DrugCentral, RxNorm, PubChem, and INKEEDecoder by name or identifiers to retrieve evidence-grouped records and source-attributed conflicts.

Instructions

Search ingredients across openFDA, CosIng, DrugCentral, RxNorm, PubChem, and INKEEDecoder. Start free text with type 'name'; use inci, unii, cas, ec, rxcui, or cid when that is the value you have. There is no ingredient category filter. Returns evidence-grouped entities with original records, confirmed links, source-attributed conflicts, unconfirmed candidates, and per-entity nextSteps. For source+id use drugdata_get_ingredient instead. Default searches return lightweight evidence without identity resolution; resolve_identities: true opts in to enrichment of at most five entities, concurrency three, within the shared 45-second default deadline. Read partial, coverage, and sources (status ok/error/timeout); completed results survive a timeout. One page applies to every source and re-queries all of them; each source's hasMore is independent. Selectively fetch supplied URLs only when more page content is needed. No matches is normal, not an error.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "query": "<query>"
    },
    "name": "drugdata_search_ingredients"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number for the fan-out, starting at 1. One page applies to every source and re-queries all of them.
typeYesWhat to search by: 'name', 'inci' (INCI name), 'unii', 'cas' (CAS Registry Number), 'ec' (EC number), 'rxcui' (RxNorm concept id), or 'cid' (PubChem compound id).
queryYesThe search value, as text or an identifier.
response_formatNoText format: 'markdown' for a readable grouped report, or 'json' for the structured result serialized as JSON.markdown
resolve_identitiesNoOpt in to identity enrichment for at most five entities, concurrency three. Default false: return lightweight search evidence and resolution nextSteps.

Output Schema

NameRequiredDescriptionDefault
pageYes
typeYes
queryYes
partialYes
sourcesYes
coverageYes
entitiesYes
nextStepsYes
truncatedYes
entitiesOmittedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the bar is lower; the description nonetheless adds substantial behavior: default results are lightweight with no identity resolution, resolve_identities is capped at five entities with concurrency three inside a shared 45-second deadline, completed results survive a timeout, and 'No matches is normal, not an error'. It also explains how to read partial/coverage/sources status — context an agent could not derive from annotations.

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

Conciseness4/5

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

Purpose and source list are front-loaded, then routing rules, then behavioral caveats — a sensible order with no filler sentences. It is dense and long for one paragraph, packing pagination, timeouts, and status semantics together, which slightly hurts scanability but every sentence carries information.

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

Completeness5/5

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

For a five-parameter federated search with an output schema, the description covers what an agent still needs: result shape orientation (evidence-grouped entities with conflicts and unconfirmed candidates), partial-failure handling, timeout survival, and pagination independence per source. Nothing needed to call it correctly or interpret degraded responses is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, and the description adds real meaning: it pairs query content to the correct type value and clarifies that one page applies to every source and re-queries all of them, with each source's hasMore independent. Some of this (page fan-out wording, resolve_identities caps) overlaps with schema descriptions, so it is additive rather than fully compensating for gaps.

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

Purpose5/5

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

States a specific verb (search) and resource (ingredients) and enumerates the six federated sources, so the agent knows this is a multi-source fan-out search rather than a single-source lookup. It explicitly contrasts itself with the sibling drugdata_get_ingredient ('For source+id use drugdata_get_ingredient instead'), making the boundary clear without opening either schema.

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

Usage Guidelines5/5

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

Gives concrete routing rules: free text starts with type 'name', and identifier types (inci, unii, cas, ec, rxcui, cid) are used 'when that is the value you have'. It also names the alternative for source+id lookups and rules out an ingredient category filter, which prevents a wasted call pattern.

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