# Clarity by Health AI (remote · mcp.healthai.com)

Condition-aware ingredient and product checks for agents, with evidence tiers and citations.

- Trust score: 74/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.healthai.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/com-healthai-clarity/mcp.md), [page](https://verifymcp.io/servers/com-healthai-clarity/mcp)

## Channel facts

- Endpoint: `https://mcp.healthai.com`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.7.8`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1785 tokens (~162/item across 11 items; 9 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 21/100
  - Stability check failed: schema churn in the 8 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-healthai-clarity https://mcp.healthai.com/
```

### Codex

```toml
[mcp_servers.com-healthai-clarity]
url = "https://mcp.healthai.com/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-healthai-clarity": {
      "type": "remote",
      "url": "https://mcp.healthai.com/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-healthai-clarity --url https://mcp.healthai.com/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-healthai-clarity:
    url: "https://mcp.healthai.com/"
```

### Other

```json
{
  "mcpServers": {
    "com-healthai-clarity": {
      "type": "http",
      "url": "https://mcp.healthai.com/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 14 to 18.

### 2026-08-01 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 11 to 14.

### 2026-07-31 (score 72, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 71, +3)

- [security regression] Stability: 0.10 → fail
- [security improvement] Authorization: unverified → partial
- [functional] First check of Tool coverage: 100

### 2026-07-29 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 66, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 66)

First indexed and scored.

## MCP tools (9)

### `check_ingredient` (~180 tokens)

Check an ingredient

Look up a cosmetic/food/supplement ingredient in Clarity's condition-aware database. Returns verdict, evidence tier (Gold/Silver/Bronze), and citation for a given condition lens. Pass `lenses` (array) instead of `lens` to check several conditions in ONE call (profile-shaped checking, e.g. a user who is pregnant AND has MCAS) — results then carry a per-lens breakdown under `lenses{}`. Every result includes human_url, a live Clarity page to hand the user as the source link.

Input parameters:

- `lens` (string): Single condition lens
- `lenses` (array): Multiple condition lenses in one call (max 5); wins over `lens` when provided
- `name` (string, required): Ingredient name, e.g. 'niacinamide' or 'aged cheddar cheese'

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `check_stack` (~166 tokens)

Audit a supplement stack

Audit a supplement/ingredient STACK in one call: per-item condition-lens verdicts (evidence-graded, cited where citations exist) PLUS every curated ingredient-to-ingredient interaction found WITHIN the stack (type, severity, mechanism, source). Use when a user takes multiple supplements together. Supports multi-lens via `lenses`. Absence of an interaction is NOT proof of safety — the curated set is growing. Every result includes human_url for the user.

Input parameters:

- `ingredients` (array, required): 2-12 ingredient/supplement names, e.g. ['iron','calcium','quercetin']
- `lens` (string): Single condition lens
- `lenses` (array): Multiple condition lenses in one call (max 5); wins over `lens` when provided

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `find_alternatives` (~195 tokens)

Find safer product alternatives

Find 2-3 safer swaps for a flagged product: same-category products that rate good/excellent on Clarity's general food/skincare quality score AND contain no ingredient flagged for the given condition lens. Seed by barcode (preferred — e.g. right after scan_barcode flags something) or product_name. Each alternative carries its score, ingredient-recognition coverage, and human_url. The score is a GENERAL quality score, not a condition verdict — verify a chosen alternative with scan_barcode or check_stack. Food and skincare only (supplement swaps are declined honestly for now).

Input parameters:

- `barcode` (string): UPC/EAN of the product to swap away from (6-14 digits)
- `count` (integer): How many alternatives to return (1-5)
- `lens` (string): Condition lens for the ingredient screen
- `product_name` (string): Product name to seed from when no barcode is available

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `strain_lookup` (~62 tokens)

Look up a cannabis or mushroom strain

Look up a cannabis or mushroom species/strain in Clarity's database. Returns verdict, evidence tier, PMID citation, and safety flags.

Input parameters:

- `species` (string, required): Species or strain name, e.g. 'Cannabis sativa' or 'Lion's Mane'

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `scan_barcode` (~128 tokens)

Scan a product barcode

Look up a product by barcode (Open Food Facts / Open Beauty Facts), match its ingredients against Clarity's database, return which ingredients are flagged for the given condition lens, AND flag any active FDA recall for the product (recall_flag + recalls[], sourced from FDA — verify via source_url). On a local-mirror miss, the tool may query Open Food/Beauty Facts, refresh Clarity's product mirror, and count unmatched ingredient tokens for coverage improvement.

Input parameters:

- `barcode` (string, required): UPC/EAN barcode, 6-14 digits
- `lens` (string): Condition lens

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `validate_claim` (~166 tokens)

Validate a health claim

Fact-check a free-text health/safety claim against Clarity's human-curated, evidence-graded database. Given a statement (e.g. 'fenugreek is safe while breastfeeding') and a condition lens, returns whether Clarity's curated position supports / contradicts / does-not-cover it, plus any verified citation on file. Use this to check whether a health claim an agent already holds aligns with Clarity's curation. Uncovered statements may be counted in Clarity's review queue; do not include personal information. Descriptive — not medical advice.

Input parameters:

- `lens` (string): Condition lens the claim is about
- `statement` (string, required): The health/safety claim to validate, e.g. 'niacinamide is safe during pregnancy'. Do not include personal information.

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `check_interaction` (~174 tokens)

Check ingredient interactions

Check Clarity's curated ingredient-to-ingredient interaction database. Give one ingredient to list everything it interacts with (e.g. 'iron'), or two ingredients to check a specific pair (e.g. 'calcium' + 'iron'). Returns interaction_type, severity (Beneficial/Moderate/High), mechanism, clinical_note, source, and whether it affects lactation/infant/absorption. Queries both directions of the pair. Absence of a result is NOT proof of safety — the set is curated and growing. Descriptive with sources, not medical advice.

Input parameters:

- `ingredient_a` (string, required): The ingredient to check, e.g. 'iron' or 'calcium'
- `ingredient_b` (string): Optional second ingredient to check a specific pair. Omit to list all interactions for ingredient_a.

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `score_product` (~147 tokens)

Score a product

Get Clarity's product quality score by barcode. Returns category-specific scores (food: nutrition/additive/processing/organic; skincare: irritation/allergen/endocrine/condition; supplement: transparency/safety/label_quality/complexity — dose transparency penalizes proprietary blends, safety flags high-risk botanicals) — these are DISTINCT and never merged — plus per-lens fit with match coverage. Always includes data_quality/coverage so a score is never given without its confidence.

Input parameters:

- `barcode` (string, required): UPC/EAN barcode, 6-14 digits
- `category` (string): Product category (omit for auto)
- `lens` (string): Condition lens for per-lens fit

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

### `check_recall` (~170 tokens)

Check a consumer-product recall

Check whether a consumer product or brand has an FDA/consumer recall on file — supplements, food, cosmetics (NOT medical devices). Query by `brand` (primary), optionally narrow by `product_name`. Returns recall_flag, whether any active Class I (most serious) recall exists, and each matching record with classification, reason, date, status, and a source_url to verify. Recall data has no barcode, so matches are brand/name text matches — confirm via source_url. For medical-DEVICE recalls, use the radar MCP (com.healthai/radar).

Input parameters:

- `brand` (string, required): Brand or manufacturer name, e.g. 'Nature Made' or 'Similac'
- `product_name` (string): Optional product name to narrow within the brand, e.g. 'infant formula'

Output parameters:

- `disclaimer` (string): Informational-use and medical-advice limitation.
- `error` (string): Actionable input or availability error when the tool cannot return a result.
- `human_url` (string): A live Clarity page or checker URL that the user can open for context.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-healthai-clarity/mcp#diagnostics

## Score history

- 2026-08-03: 74
- 2026-08-02: 74
- 2026-08-01: 73
- 2026-07-31: 72
- 2026-07-30: 71
- 2026-07-29: 68
- 2026-07-28: 67
- 2026-07-27: 66
- 2026-07-26: 66

## Links

- Remote endpoint: https://mcp.healthai.com/
- Repository: https://github.com/healthai-hq/clarity-project
- Website: https://healthai.com/clarity/api/
- Changelog RSS feed: https://verifymcp.io/servers/com-healthai-clarity/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-healthai-clarity/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-healthai-clarity/mcp