FDA Approvals MCP
guptaprakhariitr/fda-approvals-mcp
Consultas estruturadas em dados regulatórios da FDA via MCP
Ver no GitHubServidor MCP que encapsula a API openFDA, fornecendo acesso estruturado a aprovações de fármacos, recalls, eventos adversos e liberações de dispositivos 510(k). Ideal para análise regulatória, pesquisa clínica e due diligence em biotech.
Instalação
npx convez-ai guptaprakhariitr/fda-approvals-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Pesquisa de aprovações de novos fármacos (NDA/BLA) por data e fabricante
- Análise de recalls de medicamentos e dispositivos por classe e período
- Consulta de eventos adversos (FAERS) e relatórios de segurança
- Due diligence em startups de biotech e análise de portfólio regulatório
- Enriquecimento de agentes de LLM clínicos com dados regulatórios reais
Veredito

MCP bem estruturado que democratiza acesso a dados FDA públicos. Estado scaffolded, mas arquitetura sólida e claro roadmap. Caso de uso legítimo em compliance e pesquisa — esperamos por implementação completa e tiers de premium (normalização de nomes, deduplicação FAERS).
README
A tradução para o português deste README ainda está na fila.
fda-approvals-mcp — SCAFFOLD
Drug approvals, device clearances (510(k)), recalls, adverse events. Wraps the openFDA free API. Sister product to
sec-edgar-mcp— same patterns, biotech audience instead of finance.
Status: scaffolded. Idea #4 in ../../../ai-as-customer-ideas.md.
Planned tools
| Tool | openFDA endpoint | Notes |
|---|---|---|
fda_drug_approval_search(date_range, sponsor?, indication?) | /drug/drugsfda.json | New drug approvals (NDA/BLA). |
fda_drug_label(drug_name) | /drug/label.json | Full drug label text. |
fda_recall_search(class?, date_range) | /drug/enforcement.json, /device/enforcement.json | Class I/II/III recall events. |
fda_adverse_events(drug_name, date_range) | /drug/event.json | FAERS adverse event reports — count + breakdown. |
fda_510k_search(date_range, sponsor?) | /device/510k.json | Premium tier: device 510(k) clearances. |
fda_drug_shortages() | drug shortage list | Premium. |
Audience
- Clinical-LLM teams (Hippocratic, Glass, OpenEvidence, AmazeVet, Scribeberry).
- Pharma research analysts.
- Biotech / pharma investor agents (cross-sells with
sec-edgar-mcp). - Journalists covering pharma.
Pricing (proposed)
Same tier shape as SEC EDGAR. Slightly higher willingness-to-pay in pharma → bias toward Team/Pro upsells.
Open / closed split
- Open: MCP shim, openFDA wrapper (it's literally a public API; no moat).
- Closed: alerts/subscriptions, drug-name normalization (RxNorm cross-ref), de-duplication of FAERS reports (multiple reporters per event), enriched label parsing.
Build steps
Same as SEC EDGAR. openFDA is even cleaner than EDGAR — JSON-RPC-compatible payloads, no User-Agent gymnastics, generous rate limits.
See also
../sec-edgar-mcp/— reference implementation.../drug-interaction-mcp/— pairs with this for clinical audience.../README.md— Category 1 pipeline.
Sister MCPs
All from the same operator, all live on <product>.prakhar-cognizance.workers.dev, all free-tier friendly:
| Group | Products |
|---|---|
| Research | sec-edgar · arxiv · world-bank-economic · uspto-patents · fda-approvals |
| Verification + Utility | verification ⭐ · unit-converter |
| India | indic-normalize · indian-regulatory |
| Real-time | hn-trending · wikipedia-recent-changes · gdelt-events · crypto-prices |
| Healthcare | drug-interaction |
| Logistics | multi-carrier-tracking |
Full catalog: https://github.com/guptaprakhariitr · ⭐ = empty-quadrant / highest-conviction pick.