Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/thehealthai/clarity-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/thehealthai/clarity-mcp/clarity)<a href="https://agentmods.dev/mcp/thehealthai/clarity-mcp/clarity"><img src="https://agentmods.dev/badge/mcp/thehealthai/clarity-mcp/clarity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/thehealthai/clarity-mcp/clarity"><img src="https://agentmods.dev/badge/mcp/thehealthai/clarity-mcp/clarity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clarity scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"clarity": {
"url": "https://mcp.healthai.com",
"type": "streamable-http"
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 6 lines scan A 23bf07ad0173
clarity is an MCP server published in the GitHub repository thehealthai/clarity-mcp (0 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
easydocforms-mcp
MCP server "easydocforms-mcp" as configured in easydocforms/easydocforms-mcp. Runs in Docker (ghcr.io/easydocforms/easydocforms-mcp:0.1.2). Needs 2 environment variables to run.
opdstar-nhi
The MCP server for Taiwan NHI billing intelligence — rejection codes, audit clauses, drug payment rules, fee schedule, special materials, and appeal case precedents. Helps AI agents answer Taiwan health-insurance billing and audit questions with authorita. Runs locally from the @opdstar/nhi-mcp npm package.
automatedrcm-billing-mcp
Medical-billing tools for AI agents: prior-auth checks, denial decoding, claim triage, appeals. Runs locally from the automatedrcm-billing-mcp npm package. Needs 1 environment variable to run.
loacare-healthcare-pricing
Search source-labeled hospital prices, CPT codes, providers, and healthcare cost estimates. Remote server at www.loacare.com.
behavior-mcp
MCP server "behavior-mcp" as configured in putervision/state-memory-mcp. Launched with behavior-mcp run. Needs 1 environment variable to run.
hypermnesia-mcp
Scientifically-grounded memory system based on computational neuroscience research. Runs locally from the hypermnesia-mcp Python package.