Skip to main content
Glama
Open Drug Data MCP
by knorby

Get one ingredient profile from an open drug data source

drugdata_get_ingredient
Read-onlyIdempotent

Fetch an ingredient profile by source-specific ID from openFDA, CosIng, DrugCentral, RxNorm, INKEEDecoder, or PubChem, returning identifier crosswalks, regulatory notices, and links.

Instructions

Use this for an existing source+id, including an entity record or confirmed link; do not repeat a broad search. Fetch only needed records; selectively fetch supplied URLs with host web tools if more page content is needed. Fetch one ingredient profile from openFDA, CosIng, DrugCentral, RxNorm, INKEEDecoder, or PubChem. The id is the database's own key: a UNII or dashed CAS number (openfda), a numeric substance id or exact INCI/glossary name (cosing), a numeric structure id, UNII, dashed CAS number, or a supported TYPE:value crosswalk identifier (drugcentral), a numeric RxCUI (nlm), an ingredient slug/URL (inkeedecoder), or a numeric PubChem CID (pubchem). The result carries the unified ingredient ref, the source's profile fields and identifier crosswalk, verbatim regulatory notices where the source publishes them, links, and suggested follow-up calls. include_clinical asks DrugCentral for indications, off-label uses, contraindications, and FAERS counts — extra requests, verbose, default false. include_cosing_panel asks INKEEDecoder to include its CosIng CAS/EC/IUPAC panel from the same page fetch — no extra request, default false. A malformed id is an error result naming the search tool that finds a valid one; an upstream miss is an error result, not an empty profile.

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": {
      "source": "<source>",
      "id": "<id>"
    },
    "name": "drugdata_get_ingredient"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe database's own identifier: UNII or dashed CAS (openfda), substance id or INCI/glossary name (cosing), structure id, UNII, CAS, or TYPE:value crosswalk id (drugcentral), numeric RxCUI (nlm), slug/URL (inkeedecoder), or numeric PubChem CID (pubchem).
sourceYesUpstream database that owns the record: 'openfda', 'cosing', 'drugcentral', 'nlm', 'inkeedecoder', or 'pubchem'.
response_formatNoText format: 'markdown' for a readable profile, or 'json' for the structured result serialized as JSON.markdown
include_clinicalNoDrugCentral only: fetch indications, off-label uses, contraindications, and FAERS counts. Extra requests and often verbose — default false.
include_cosing_panelNoINKEEDecoder only: include the CosIng panel (CAS numbers, EC numbers, IUPAC name) from the same page fetch — no extra request. Default false.

Output Schema

NameRequiredDescriptionDefault
linksYes
profileYes
nextStepsYes
ingredientYes
regulatoryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing per-source id formats, what the result contains (unified ref, profile fields, crosswalk, verbatim regulatory notices, links, suggested follow-ups), and the two distinct error modes (malformed id vs. upstream miss returning an error rather than an empty profile). It also flags the cost profile of each optional flag — extra verbose requests for include_clinical versus no extra request for include_cosing_panel.

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?

Front-loads the usage condition and exclusion, then the source list, then id semantics, then flag notes — a sensible order with no filler sentences. It is dense and repeats some schema content (id formats appear twice), which keeps it from a 5.

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, six-source fetch tool with an output schema, the definition covers when to call it, how ids are keyed per source, what comes back, and both failure modes. Nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so the schema already documents every parameter including the id format list and the flag descriptions; the description largely restates that content. It adds some practical color (include_clinical is verbose and costs extra requests), but omits response_format entirely, so the baseline 3 is appropriate.

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 precise verb and resource ('Fetch one ingredient profile') and enumerates the six upstream sources by name, so the agent knows exactly which universe of records this covers. It also contrasts itself with search behavior ('do not repeat a broad search'), distinguishing it from drugdata_search_ingredients without needing the sibling's schema.

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

Usage Guidelines4/5

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

Gives a clear precondition ('for an existing source+id, including an entity record or confirmed link') and an explicit exclusion ('do not repeat a broad search'), plus a note that a malformed id returns an error pointing at the search tool. It stops short of naming the discovery sibling outright, leaving the agent to infer that search is the alternative.

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