Drug Interaction MCP
guptaprakhariitr/drug-interaction-mcp
Verificador de interações medicamentosas com alta rastreabilidade para startups clínicas
Ver no GitHubServidor MCP para verificação de interações medicamentosas em LLMs clínicos, integrando dados de RxNorm, openFDA e DailyMed. Fornece ferramentas para normalizar nomes de fármacos, verificar interações pairwise, consultar guias de dosagem e encontrar alternativas terapêuticas com rastreabilidade de fontes.
Instalação
npx convez-ai guptaprakhariitr/drug-interaction-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
- Apoio à decisão clínica em LLMs médicos (Hippocratic, Glass, OpenEvidence)
- Verificação de polifarmácia em tempo real
- Normalização de nomes de medicamentos e busca de alternativas terapêuticas
Veredito

High-stakes healthcare tool com forte foco em conformidade e rastreabilidade de fontes. Ainda em fase de scaffold, mas direcionado a mercado premium (startups clínicas) dispostas a pagar $99+/mês. Requer rigor absoluto em validação de dados e disclaimers médicos.
README
A tradução para o português deste README ainda está na fila.
drug-interaction-mcp — SCAFFOLD
Drug-drug interaction checker for clinical LLMs. Wraps RxNorm + openFDA + DailyMed. High-stakes use case → high willingness-to-pay (clinical LLM startups).
Status: scaffolded. Idea #20 in ../../../ai-as-customer-ideas.md.
Planned tools
| Tool | Source | What it returns |
|---|---|---|
check_interaction(drug_a, drug_b) | RxNorm + DailyMed | Severity (contraindicated / major / moderate / minor), mechanism, references. |
check_interactions_multi(drug_list[]) | RxNorm | Pairwise matrix for a polypharmacy regimen. |
dose_guide(drug, condition?, age_band?) | DailyMed labels | Indication-specific dose ranges. Premium. |
normalize_drug_name(name_or_brand) | RxNorm | Map brand to generic (RxCUI). |
find_alternatives(drug, condition?) | RxNorm class hierarchy | Same-class alternatives. Premium. |
Audience
Clinical LLM startups (Hippocratic, OpenEvidence, Glass, etc.). High-stakes use case → they pay $99+/mo without blinking when it works.
Pricing (higher than peers)
| Tier | Price | Notes |
|---|---|---|
| Free | $0 | 50 calls/mo (clinical, conservative) |
| Solo | $29 | 1,000 |
| Team | $99 | 10,000 + dose_guide + find_alternatives |
| Pro | $299 | 100,000 + alerts + custom interaction-table import |
Risk notes
- This is high-stakes. Bad data could harm patients. Clinical buyers will absolutely audit your sources.
- Cite every interaction back to its source (DailyMed label section, RxNorm relationship). Make sources part of the response payload, not an afterthought.
- Add disclaimer in every response: "For clinical decision support; final responsibility rests with the prescriber."
- Possibly: insurance / SOC2 path eventually. For initial launch, just be honest about sources + freshness.
Open / closed split
- Open: RxNorm wrapper, drug normalization, basic interaction lookup.
- Closed: interaction-severity scoring, alternative-finding logic, the precomputed interaction matrix (the data is from CMS but the index and severity scoring is the moat).
See also
../fda-approvals-mcp/— same 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.