Condition-aware ingredient & product safety for AI agents: verdict, evidence tier, citations.
Connect Clarity By Health AI to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Condition-aware ingredient & product safety for AI agents: verdict, evidence tier, citations. The clarity by health ai mcp server is what makes that connection.
Condition-aware ingredient & product safety intelligence for AI agents. Every answer carries a verdict, an evidence tier (Gold / Silver / Bronze), and a citation — curated against authoritative sources (LactMed, InfantRisk, PubMed, DSLD, DermNet, EU CosIng) by Health AI (Dr. Olga Lavinda, PhD).
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
check_ingredient — Verdict + evidence tier + citation for a cosmetic/food/supplement ingredient, under a condition lensstrain_lookup — Verdict, tier, PMID citation and safety flags for a cannabis or mushroom species/strainscan_barcode — Look up a product by UPC/EAN, flag its ingredients for a condition lens, and surface any active FDA recallvalidate_claim — Fact-check a free-text health claim against Clarity's curated position — supports / contradicts / does-not-cover, with citationcheck_interaction — Curated ingredient-to-ingredient interactions — type, severity, mechanism, clinical note, source (single or pair)score_product — Category-specific product quality score by barcode (food / skincare / supplement), each dimension distinct, always with data-quality coveragecheck_stack — Audit a supplement/ingredient stack in one call — per-item condition-lens verdicts (cited where evidence exists) plus curated within-stackfind_alternatives — Find 2–3 safer same-category swaps for a flagged product, rated on Clarity's quality dimensionscheck_recall — Check whether a consumer product or brand has an active FDA/consumer recall on file (food, supplements, cosmetics — not devices), with classificationBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Clarity By Health AI's toolset — check_ingredient, strain_lookup, scan_barcode and 6 more — is a fair guide to whether it matches your workflow. It is maintained by com.healthai; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Clarity By Health AI's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| check_ingredient | Verdict + evidence tier + citation for a cosmetic/food/supplement ingredient, under a condition lens |
| strain_lookup | Verdict, tier, PMID citation and safety flags for a cannabis or mushroom species/strain |
| scan_barcode | Look up a product by UPC/EAN, flag its ingredients for a condition lens, and surface any active FDA recall |
| validate_claim | Fact-check a free-text health claim against Clarity's curated position — supports / contradicts / does-not-cover, with citation |
| check_interaction | Curated ingredient-to-ingredient interactions — type, severity, mechanism, clinical note, source (single or pair) |
| score_product | Category-specific product quality score by barcode (food / skincare / supplement), each dimension distinct, always with data-quality coverage |
| check_stack | Audit a supplement/ingredient stack in one call — per-item condition-lens verdicts (cited where evidence exists) plus curated within-stack interactions |
| find_alternatives | Find 2–3 safer same-category swaps for a flagged product, rated on Clarity's quality dimensions |
| check_recall | Check whether a consumer product or brand has an active FDA/consumer recall on file (food, supplements, cosmetics — not devices), with classification + source URL |
{
"mcpServers": {
"clarity": {
"command": "npx",
"args": ["-y", "wrangler"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.