health-ai-claritySAFE
Condition-aware ingredient & product safety MCP server — 9 tools, every answer with a verdict, evidence tier, and citations. com.healthai/clarity on the official MCP registry. Hosted at mcp.healthai.com.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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](https://healthai.com/clarity/mcp/).
Use it
Claude Code:
claude mcp add --transport http clarity https://mcp.healthai.com
Claude 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."
});Tools (9)
fb28623c3b1aOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add clarity-mcp --env CLARITY_MCP_API_KEY=${CLARITY_MCP_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"clarity-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CLARITY_MCP_API_KEY": "${CLARITY_MCP_API_KEY}"
}
}
}
}Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
CLARITY_MCP_URL: `http://127.0.0.1:${address.port}`,Gates applied: no_behavioural_pass.
fb28623c3b1afull audit observations/trust-audit/mcp-server/thehealthai__clarity-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | fb28623c3b1a | SAFE | B | 89 | first audit |
Questions
What is the health-ai-clarity MCP server?
Condition-aware ingredient & product safety MCP server — 9 tools, every answer with a verdict, evidence tier, and citations. com.healthai/clarity on the official MCP registry. Hosted at mcp.healthai.com.
Is health-ai-clarity safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does health-ai-clarity need?
It reads CLARITY_MCP_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does health-ai-clarity run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as clarity-mcp at 0.7.8.
How current is this page?
The grade is for one exact copy of the source (fb28623c3b1a), read on 2026-10-12. The repository is watched and re-audited when it changes.