Clarity MCP
Clarity MCP is a condition-aware ingredient and product safety checker for health, wellness, and fitness applications. It provides verdicts, evidence tiers (Gold/Silver/Bronze), citations, and safety information. Capabilities include:
Ingredient checking –
check_ingredient: Returns a verdict, evidence tier, citation, and human-readable URL for any cosmetic, food, or supplement ingredient, filtered by one or multiple condition lenses (e.g., pregnancy, MCAS, histamine, rosacea, breastfeeding).Supplement stack audits –
check_stack: Analyzes 2–12 supplements together, providing per-item condition verdicts and curated ingredient-to-ingredient interactions within the stack, including type, severity, and mechanism.Find safer alternatives –
find_alternatives: Suggests 2–5 safer, same-category swaps for a flagged food or skincare product, ranked by quality score and screened against a chosen condition lens.Strain lookup –
strain_lookup: Provides verdicts, evidence tiers, PMID citations, and safety flags for cannabis or mushroom species/strains.Barcode scanning –
scan_barcode: Looks up a product by UPC/EAN, flags ingredients for a condition lens, and surfaces active FDA recalls.Claim validation –
validate_claim: Fact-checks free-text health statements against Clarity's curated database, indicating whether the claim is supported, contradicted, or not covered, with citations where available.Interaction checking –
check_interaction: Lists all known interactions for a single ingredient or checks a specific pair, with severity, mechanism, clinical notes, and sources.Product scoring –
score_product: Gives category-specific quality scores (food, skincare, supplement) by barcode, with dimension breakdowns, per-lens fit, and data coverage confidence.Recall monitoring –
check_recall: Searches for FDA/consumer recalls by brand and optional product name for supplements, food, and cosmetics (not medical devices), providing classification, reason, and source URLs.
Clarity MCP — com.healthai/clarity
Clarity is a condition-aware ingredient checker and scanner for wellness, fitness, tracker, and health-AI workflows. Results can include a verdict, an evidence tier (Gold/Silver/Bronze), and citations when available.
Hosted MCP server — no install and no key required for anonymous,
rate-limited access. Endpoint:
https://mcp.healthai.com (Streamable HTTP, JSON-RPC 2.0). Published to the
official MCP Registry as com.healthai/clarity (domain-verified namespace).
For a human-readable implementation guide covering Claude.ai, Claude Code, OpenAI's Responses API, generic remote MCP configuration, tool boundaries, and the MCP-versus-REST decision, see healthai.com/clarity/mcp.
Use it
Claude Code:
claude mcp add --transport http clarity https://mcp.healthai.comClaude Desktop / Cursor / any client with native remote MCP — add to the
config's mcpServers:
{
"mcpServers": {
"clarity": {
"type": "streamable-http",
"url": "https://mcp.healthai.com"
}
}
}For older clients without native remote support, bridge with mcp-remote:
"command": "npx", "args": ["-y", "mcp-remote", "https://mcp.healthai.com"].
OpenAI Responses API: pass the hosted endpoint as a remote MCP tool and keep approvals enabled while evaluating it:
import OpenAI from "openai";
const client = new OpenAI();
const response = await client.responses.create({
model: "gpt-5.6",
tools: [{
type: "mcp",
server_label: "clarity",
server_url: "https://mcp.healthai.com",
require_approval: "always"
}],
input: "Audit iron, calcium, and magnesium for pregnancy and interactions."
});Related MCP server: Scientific Tools MCP Server
Tools (9)
Tool | What it answers |
| Verdict + evidence tier + citation for a cosmetic/food/supplement ingredient, under one condition lens or several at once ( |
| Audit a supplement stack in one call: per-item condition verdicts plus every curated interaction within the stack |
| Safer same-category swaps for a flagged product — general quality-score ranked, lens-flag screened, coverage-honest (food/skincare; verify the pick with |
| Verdict, tier, PMID citation and safety flags for a cannabis or mushroom species/strain |
| Look up a product by UPC/EAN, flag its ingredients for a condition lens, and surface any active FDA recall |
| Fact-check a free-text health claim against Clarity's curated position — supports / contradicts / does-not-cover, with citation |
| Curated ingredient-to-ingredient interactions — type, severity, mechanism, clinical note, source (single or pair) |
| Category-specific product quality score by barcode (food / skincare / supplement), each dimension distinct, always with data-quality coverage |
| Consumer-product recall matches by brand and optional product name, with source URLs and a medical-device scope boundary |
Condition lenses: breastfeeding, lactation, pregnancy, histamine,
mcas, rosacea, hs, allergy, all.
Every result includes human_url — a live Clarity page for that exact answer
(gated against the site's keep-list so it never 410s), for agents to hand their
user as the source link. The server also exposes MCP prompts
(audit_supplement_stack, fact_check_health_claim, product_safety_check) and
resources (clarity://methodology, clarity://lenses).
Anonymous use is rate-limited to 60 tool calls/min per IP (Durable Object
limiter); add an X-API-Key header for higher metered limits. The
scan_barcode live fallback can refresh Clarity's product mirror and count
unmatched ingredient tokens. Uncovered validate_claim statements can be
counted in the review queue, so inputs must not contain personal information.
Descriptive — not medical advice; absence of a flag is not proof of safety.
For MCP transport security, non-browser clients may omit Origin. Requests to
the MCP endpoint that include Origin must match the requested endpoint's
origin exactly; mismatches return HTTP 403.
Data handling
Tool inputs can include ingredient or product names, condition lenses,
supplement stacks, barcodes, ingredient pairs, and free-text health claims.
Every tool call writes bounded operational telemetry for reliability, abuse
prevention, and latency monitoring. That telemetry includes the tool name,
keyed/anonymous status, condition lens, a short request fingerprint, status,
and duration; it does not include raw tool arguments. scan_barcode may query
Open Food Facts or Open Beauty Facts and refresh a private Clarity mirror.
Uncovered validate_claim text may enter a private review queue.
Do not send names, contact details, medical records, or other personal information. Review the public privacy policy before connecting this server.
Runnable direct, LangChain, LlamaIndex, Cloudflare Agents, and Hugging Face
client examples live in examples/mcp.
This repository is the curated public developer surface for the hosted server: setup, examples, metadata, and the stdio bridge. Production implementation, deployment configuration, credentials, and operational data are maintained separately.
Maintenance
Related MCP Servers
- AlicenseAquality-maintenanceSupplement safety MCP server for AI agents. FDA FAERS signals, CYP450 pathways, 584 compound aliases. Works with Claude Desktop, LangChain, CrewAI.51
- FlicenseAqualityDmaintenanceHigh-value scientific tools for AI agents — literature search (PubMed, arXiv, Semantic Scholar), chemical compound lookup (PubChem, ChEMBL), patent prior art search (USPTO, EPO), GPU spot prices across 4 providers, and real-time earth science data (USGS, NASA, OpenAQ). Per-call billing via API key. Keys issued instantly at https://mcp-site.com/keys/request6
- AlicenseAqualityBmaintenanceEvidence-based supplement recommendation MCP server covering 17 supplements and 40+ conditions with medication interaction checking and form quality classification.573MIT

citedhealth-mcpofficial
Alicense-qualityCmaintenanceMCP server for CITED Health that allows AI assistants to query evidence-based supplement data, including ingredient evidence grades, health conditions, PubMed papers, glossary terms, and educational guides.MIT
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Hosted MCP server exposing US hospital procedure cost data to AI assistants
A paid remote MCP for AI SDK MCP gateway registry, built to return verdicts, receipts, usage logs, a
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thehealthai/clarity-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server