DrugCore and RegulatoryCore are now live in the API and MCP. Read more

Amass
MCP showcasesResmetirom evidence snapshot

MCP Showcase

Resmetirom evidence snapshot

Name a drug asset; get a one-page PDF evidence snapshot — regulatory status, pivotal trials, grounded efficacy figures and the trial↔paper link — every number verbatim from Amass.

See the prompt

New to Amass? Connect Amass to Claude first

2MAESTRO trials
2024FDA approval
You getpdf1 file
Promptresearchclaude

The prompt

Paste this into Claude

Drug assetresmetirom
prompt
DRUG ASSET: resmetirom

You have the Amass MCP connected (TrialCore + BioMedCore). Produce a one-page EVIDENCE SNAPSHOT
PDF for this asset — every figure traceable to an Amass record.

1. STATUS + PIVOTAL TRIALS. Call search_amass_trialcore_records with:
     query = the DRUG ASSET + indication terms, phase = "PHASE3"
   Keep the registrational trials; capture NCT, acronym, sponsor, status and enrollment verbatim.

2. EFFICACY. Call search_amass_biomedcore_records with:
     query = the DRUG ASSET + indication terms, minJournalQualityJufo = 2, isRetracted = false
   Pull 2–3 grounded findings; quote every number (%, mg, P, fibrosis stage) VERBATIM from the
   abstract. Tag each with PMID, journal, JuFo tier, citationCount.

3. CROSS-CORE PROVENANCE. For the pivotal trial, call get_amass_trialcore_record and read its
   referencesBiomedCore links — show NCT ↔ PMID, the publication↔trial edge.

4. Lay sections 1–3 out as a single-page .pdf snapshot: a regulatory-status callout, the trial
   table, the grounded findings, and the provenance line. Close with a scope note — figures are
   verbatim from Amass records as of <date>; this is an evidence digest, not regulatory advice.

Why not just ask the model?

Ask a plain model for "a one-pager on resmetirom" and you get a confident page of unverifiable numbers — a fat-fraction here, an approval date there, a trial ID that won't resolve.

  • Plain model: invents the hepatic-fat reduction, guesses the approval date, cites an NCT that doesn't resolve.
  • Amass: −34.9% / −38.6% hepatic fat (PMID 37845512) · FDA accelerated approval, March 2024, F2–F3 fibrosis (PMID 38771485) · 56.6% vs 33.8% MASH resolution with weight loss (PMID 41127972) · NCT03900429 → PMID 41895606 — each figure copied from the record, not recalled.

Honest scope

A snapshot, not a dossier: two pivotal trials and a few grounded figures chosen to fit one page, not a complete program or a meta-analysis. MAESTRO-NASH is still ACTIVE_NOT_RECRUITING (long-term outcomes ongoing); every figure is verbatim from the cited abstract as of the run date and traceable by the PMIDs and Amass IDs on the page. An evidence digest, not regulatory advice.

Run it yourself

Connect Amass to Claude and paste the prompt.

No build, no deploy — the connector takes about a minute, then this workflow runs on your own inputs.