PillScout
Know what everything you take is doing.
Connect your medications, supplements, OTC, and compounds to Claude once. When you ask a question that matters to your cabinet, PillScout checks it against a verified safety engine: interactions, cumulative risk, condition context, pregnancy rules, and clear signals showing what's verified and what isn't.
Request a beta keyPillScout is in closed beta.
What's in the engine
PillScout runs as an MCP server that connects to Claude. When you ask about something you take, a symptom you're having, or a new prescription, it checks your full cabinet against a layered safety engine rather than reasoning from memory alone.
Persistent cabinet. Connect once. Your full list travels across every Claude conversation. No re-listing what you take every time you ask.
Verified ingredient profiles. 151 profiles with citations covering the medications, supplements, and compounds people actually take.
Cumulative risk scoring. Anticholinergic burden, CNS depression, QTc prolongation, and serotonin load, scored across your full cabinet rather than pair-by-pair.
Patient context. Age, conditions, pregnancy and lactation status travel with your cabinet. Beers Criteria runs automatically for adults 65+. Pregnancy and lactation rules apply when they should, and don't apply when they shouldn't.
Symptom-to-cabinet mapping. Tell Claude what you're feeling. PillScout maps it back to what in your cabinet could plausibly be causing it, with confidence levels for each match.
Three-tier safety architecture. Verified pairs first, static drug-class rules second, AI pharmacology reasoning last. Every answer is labeled with which tier it came from.
Coverage signals: what's checked, what isn't
Every safety engine has gaps. The question is whether it tells you where they are.
PillScout surfaces coverage signals on every analysis: what's database-verified, what's inferred from drug class rules, and what's AI-estimated pharmacology that hasn't been explicitly validated. When Claude gives you an answer, you see the lineage of that answer, not just the conclusion.
Gaps aren't failures. They're transparency. A clean result with full coverage means something. A clean result with partial coverage means something different. You get to see which one you have.
How PillScout gets better
Every time someone uses it, I see the next gap.
When an ingredient or combination isn't fully covered, that gap gets logged: just the missing piece and how often it comes up. Nothing from your cabinet, your identity, or your actual conversations is ever stored. Only the structured inputs from the safety tools are recorded.
That means the database grows based on what real people actually ask about, not on what's easiest for me to add next. The most common gaps become the next verified profiles.
I'm ScoutI don't guess at what you takeI check it
How PillScout got here
I started PillScout because the tools I wanted didn't exist. The ones that came close took too much work to be useful.
I'd see a new supplement making big claims, “helps you feel better,” “super good for you,” and immediately wonder: can I actually take this with what I'm already on?
A family member is on heart medication. Would this new thing quietly help their numbers, or make things worse? My mom takes prescriptions from different doctors and a bunch of gummy supplements, and always feels nauseous. Is one of them causing it? Could another one actually help?
Before, checking meant searching the web for each thing, trying to piece it all together myself, and usually giving up partway. AI can give you a quick answer now, but only if it knows everything you take and what's actually in each thing.
I asked my kids to build it. They said, “you build it.” So I did.
I started with a web app because that's what was possible at the time. Then MCP came along and the version I actually wanted became possible: a cabinet your AI assistant uses automatically, in every conversation, wherever you're already talking to it.
That's what PillScout was always meant to be.
Request a beta key
PillScout is in closed beta. I'm handing out keys one at a time to people who want to actually try it. Clinicians, researchers, builders, students, caregivers, and anyone curious about health tech are all welcome to ask.
Email pillscout@pillscout.health with a line about who you are and what you'd try it on. I read every one.
If you'd also like to see the beta web app, mention it in your note.