A drug question your agent shouldn’t answer from a web page

Suppose you ask an agent a narrow question about a drug. Is atorvastatin in a recruiting trial? What does PubMed return for it? Does FDA have labeling or adverse-event records? An agent that tries to answer from web pages will come back with a narrative. What you actually need is an identifier you can reuse, a status field you can check, and a timestamp for when the source last refreshed.

I called four official APIs on 16 November 2026 and wrote down what they returned. All four are listed in the AgentReady Tools catalog, in the Health and biomedical data category. None of them charged a fee for the calls I made. They also don’t share a login model, a rate limit, or a common ID. That missing common ID is the part that breaks a workflow.

The data is already in JSON. The work is calling the right endpoint with an identifier that survives the next search, and not asking any source to do more than it claims to support.

Start with the name

If an agent searches “Lipitor” in one system and “atorvastatin” in another, it can miss records that belong to the same drug. NLM’s RxNorm / RxNav APIs exist to resolve that. I called https://rxnav.nlm.nih.gov/REST/rxcui.json?name=atorvastatin and got a single RxCUI: 83367. The same host reported its dataset version as 02-Nov-2026 and apiVersion 3.1.357. I treated that RxCUI as a recorded identifier for the name I looked up. I did not assume the other three APIs would accept it as a query key.

NLM’s Terms of Service say the RxNorm, RxTerms, Prescribable RxNorm, and RxClass APIs may be used free of charge, at no more than 20 requests per second per IP address. Over that, the servers may stop servicing requests until the rate falls, and the official FAQ says the response is HTTP 429. A free UMLS license can raise the cap to 100 requests per second if you send your UTS API key as Authorization: Bearer <key>. NLM recommends caching results for 12 to 24 hours. The APIs are updated after each RxNorm full monthly release.

Most of these APIs need no license. The official FAQ makes one exception: /rxcui/{rxcui}/proprietary, which needs a UMLS license and a proxy granting ticket. RxNav’s drug/drug interaction features were discontinued on 2 January 2024, so this is the wrong API for that question. The same FAQ also notes a rename to “RxNorm Tools” on 10 February 2027, with a new site URL, and says existing functionality will not be impacted.

When I re-checked the Terms of Service and FAQ on 16 November 2026, both pages still carried NLM’s notice that, because of a lapse in government funding, information on the website may not be up to date. The API calls above still returned HTTP 200. I can’t say how that notice affects every field. An agent should surface it instead of hiding it.

The trial registry is a different API

Once you have a name or a condition, ClinicalTrials.gov is the official NLM registry API for registered studies. The current interface is version 2, documented as OpenAPI 3.0.3 at https://clinicaltrials.gov/api/oas/v2, with server URL https://clinicaltrials.gov/api/v2. The spec I fetched lists /studies, /studies/{nctId}, metadata and search-area helpers, a few /stats paths, and /version. It declares no security schemes, and I did not send a key.

A GET to /api/v2/version returned apiVersion 2.0.5 and dataTimestamp 2026-11-13T10:00:06. A GET to /api/v2/studies?pageSize=1&countTotal=true returned totalCount 611771, one study record, and a nextPageToken. I did not filter that studies call by drug name. The study it returned, NCT03772535, is not about atorvastatin, so that unfiltered call does not answer the opening question. Official pageSize defaults to 10 and is coerced down to 1,000 if you ask for more. Pages can come back with an empty studies array. If you query with only NCT IDs, filters are ignored. All of that is in the spec.

I then filtered the same endpoint. query.term=atorvastatin, documented in the OpenAPI as the “Other terms” query, returned totalCount 1257. The first study was NCT01491958, a completed atorvastatin trial. To ask the recruiting question directly, I called query.intr=atorvastatin (the official “Intervention / treatment” query) with filter.overallStatus=RECRUITING, which is one of the documented status values. That call returned totalCount 75. The first study was NCT07685938, “Pharmacologic Therapies to Mitigate Radiation- Associated Heart Disease,” with overall status RECRUITING and an intervention named “Atorvastatin and Lisinopril.” I did not review the other 74 studies. These counts will move, and a registry status is not a recommendation to use the drug.

I also tried the RxCUI as a query. query.term=83367 and query.intr=83367 both returned totalCount 0. I am not treating 83367 as a ClinicalTrials.gov query key.

I also tried an older info path, /api/info/api_vrs, and got 404. A legacy path, /api/legacy/full-studies, still returned XML, with APIVrs 1.2.0 and a DataVrs that matched the v2 timestamp. If your agent was written against the classic /api/info/ or /api/query/ URLs, check it. I’d point it at /api/v2/ now. The official OpenAPI document does not publish a request quota, and I am not going to invent one.

PubMed is a third system, with a tighter cap

PubMed / NCBI E-utilities is the official programmatic interface for PubMed and the other Entrez databases. A single unauthenticated ESearch for atorvastatin (db=pubmed, retmode=json, retmax=1) returned count 13155. That number will move. The point is the shape of the response: a count, a translation of the query, and a list of PMIDs, not a page of snippets. The first PMID in that response was 43034617.

I also tried term=83367. That call returned count 1, and the query translation was 83367[UID]. PubMed treated the number as a PubMed UID, not as an RxCUI. I am not using the RxCUI as a PubMed query key.

NCBI’s official Insights post on E-utilities API keys, still on the site when I read it, is the clearest public statement of the rate limits I could fetch today. Without a key, more than three requests per second from one IP address receives an error. A free key from your NCBI account settings raises the default to 10 requests per second for that key. You pass it as api_key. If several machines share one key, they share that budget.

I did not treat that 2017 post as a stand-in for the full E-utilities usage-policy chapter. NCBI’s Bookshelf pages presented a browser check from this network, so I could not re-read that chapter this session. If you run a heavy job, read the current policy before you loop.

openFDA will tell you not to trust it for care

openFDA is the FDA’s Elasticsearch API for public data on drugs, devices, foods, and related records, returned as JSON. Every query goes through one endpoint for one kind of data. I called https://api.fda.gov/drug/event.json?limit=1 with no key and got HTTP 200. I did not filter that call by drug name. The first record was for DURAGESIC-100, not atorvastatin, so that unfiltered call does not answer the opening question either. The meta object included last_updated 2026-10-28, a total of 21,054,159 matching records, and this disclaimer, quoted in full:

Do not rely on openFDA to make decisions regarding medical care. While we make every effort to ensure that data is accurate, you should assume all results are unvalidated. We may limit or otherwise restrict your access to the API in line with our Terms of Service.

A search of drug labels for openfda.generic_name:atorvastatin, limited to one record, also returned 200. That response said last_updated 2026-11-13, with 276 matching labels. The meta object carried the same disclaimer. The label record I got listed an openFDA rxcui of 259255, not the ingredient RxCUI 83367 I had recorded from RxNav.

A filtered adverse-event search, patient.drug.openfda.generic_name:atorvastatin, also returned 200. That response said last_updated 2026-10-28, with 252,398 matching records, and the same official disclaimer in meta. The first record included Lipitor / atorvastatin calcium among the listed drugs.

I then searched openfda.rxcui:83367 on both the label and event endpoints. Both returned HTTP 404 with the message “No matches found!” I am not treating the ingredient RxCUI 83367 as an openFDA query key.

The official authentication page lists both of the following, on the same page: “An API key is required to make calls to the openFDA API,” and standard limits for calls with no key (240 requests per minute and 1,000 per day per IP) versus calls with a free key (240 per minute and 120,000 per day per key). The key goes in the api_key query parameter, or as a basic-auth username. All queries are supposed to use https://api.fda.gov. Official query docs cap limit at 1,000 and skip at 25,000. The about page adds that not all openFDA data has been validated for clinical or production use, and that it does not include personally identifiable patient information.

If you’re wiring this into an agent, the disclaimer in meta should stay visible. It is part of the record.

What I’d do with these four

I’d resolve the name first in RxNorm and keep the RxCUI in the result as a recorded identifier. For ClinicalTrials.gov, PubMed, and openFDA, I searched with the generic name, not the RxCUI, because the RxCUI lookups above did not work as query keys in those systems on 16 November 2026. I’d also keep each source’s own identifier: NCT ID, PMID, and whatever openFDA field you actually searched.

The RxNav FAQ says a 429 means too many requests. NCBI’s rate-limit post describes an error when you exceed the cap. I did not observe a 429 or a 400 in the calls above. An empty page of studies is a valid answer in the ClinicalTrials.gov spec.

So, on 16 November 2026, here is what those opening questions actually returned from the official JSON, with the caveats already stated next to each call. The registry had 75 studies when I filtered intervention atorvastatin and overall status RECRUITING; the first was NCT07685938. That is a registry status, not medical advice, and I did not read the other 74. PubMed’s ESearch for atorvastatin returned count 13155 and a list of PMIDs. openFDA had 276 labels and 252,398 adverse-event records for generic_name:atorvastatin, each with the official disclaimer.

These four listings are in the AgentReady Tools catalog. As of 16 November 2026, /tools.json has more than 250 agent-ready tools, about 20 of them in Health and biomedical data. I didn’t re-verify the rest of that category for this post. Per-tool JSON is at /tools/rxnorm-rxnav.json, /tools/clinicaltrials-gov.json, /tools/pubmed-eutilities.json, and /tools/openfda.json. The site also publishes /llms.txt and a public, unauthenticated MCP server, com.agentready-tools/catalog, at https://agentready-tools.com/mcp. To fetch one listing, call get_tool with the exact, case-sensitive slug, for example { "slug": "rxnorm-rxnav" }. To browse the category, call search_tools with { "category": "Health and biomedical data" }. Official vendor docs and a clinician remain the authority. The catalog does not replace official limits or medical judgment.

None of this is medical advice, and none of these APIs asked me to treat it as such. If your agent is still answering that drug question from a pile of web pages, start with the name in RxNorm, search the other three APIs with the name unless you have confirmed how that system uses an RxCUI, and keep the disclaimers attached.