MCP server exposing 9 tools for pharma-intel.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/pharma-intel/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}pharma_drug_profile — Look up a drug's FDA approval status, dosage forms, interactions, and active trials. Returns approval dates, formulations, known drug interactions, and ongoing trial details. E.g., search "ozempic" or "metformin".pharma_pipeline_scan — Search clinical trials by condition (e.g., "lung cancer") or sponsor (e.g., "Pfizer"). Returns trial phases, recruitment status, and approved treatments for that indication. Pass status and phase together to answer combined questions like "how many Phase 3 obesity trials are recruiting" with the true intersection count plus a lead-sponsor tally.pharma_pipeline_catalysts — Build a sponsor catalyst-monitoring view from ClinicalTrials.gov and Drugs@FDA. Returns upcoming Phase 2/3 primary-completion dates, recently completed trials for results/disclosure follow-up, and sponsor-linked FDA applications for event-driven biotech research. Trials are those the named company LEADS as registered sponsor; a study another organisation runs using its drug belongs to that organisation and is not returned here.pharma_safety_report — Check adverse event frequency, severity patterns, and contraindications for a drug. Returns safety profiles, risk data, and recall history. E.g., search "aspirin".pharma_sponsor_diligence — Build a pharmaceutical sponsor diligence view from ClinicalTrials.gov, Drugs@FDA, and PubMed. Returns pipeline composition, recent registry activity, FDA applications, and recent affiliation-linked literature for company research.pharma_indication_landscape — Build a disease-area landscape from registered interventional trials, FDA indication-label matches, and PubMed literature. Returns sponsor, phase, status, intervention, approved-label, and publication evidence for indication research.pharma_product_sales — How much revenue a specific DRUG generates for the company that sells it — ask by brand name ("Keytruda", "Jardiance", "Eliquis") and get the reported sales figures by period and by region, straight out of the marketer's latest SEC 10-K, with the accession number and the exact filing page they came from. Bridges the gap that stops this being one lookup: FDA knows which company markets a drug, SEC knows what a company earned, and the join between them is the marketer's legal name, spelled differently in every source. Resolves brand to FDA applicant (Orange Book NDA holder or Purple Book 351(a) licence holder) to SEC filer to the product line in the disaggregated-revenue note. When the marketer is a private, foreign, or unlisted company, it says so and names them rather than returning nothing.pharma_sales_at_risk — The patent cliff, in dollars: which of a pharmaceutical company's products lose exclusivity soonest and how much reported revenue each one carries. Ask by ticker or company ("MRK", "Pfizer") for its whole portfolio ranked by expiry year, or by a single drug to place that one product. Joins the filer's own product-level revenue disaggregation from its latest 10-K to FDA exclusivity records — Orange Book listed patent and regulatory-exclusivity expirations for small molecules, Purple Book licensure and biosimilar entry for biologics — and totals revenue at risk per year. Biologics past their BPCIA 12-year floor with no biosimilar licensed (Keytruda, Gardasil) carry no FDA date and are returned separately as exposed_undated_bpcia with their own total, never assigned a year. Revenue is the last reported period, not a forecast; the expiry is the earliest date listed at FDA, before any litigation, settlement, patent-term extension, or pediatric exclusivity moves it.pharma_resolve_drug — Turn one drug name into every identifier the other pharma tools need: RxNorm RxCUI for the brand and the ingredient, FDA application numbers (NDA from the Orange Book, BLA from the Purple Book) with the sponsor on each, the DailyMed setid of the current prescribing label, the marketer's SEC CIK and ticker when it is a listed filer, the count of registered ClinicalTrials.gov studies, and the ChEMBL molecule id. Call this first when a name has to travel between regulatory, clinical, chemical, and financial sources. Every system is asked in parallel and each answer is returned with the ones that had no record left null and listed, so a gap is visible as a gap.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/pharma-intel/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io