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/aks129/HealthClawGuardrailsWrote 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/aks129/healthclawguardrails/healthclaw-local)<a href="https://agentmods.dev/mcp/aks129/healthclawguardrails/healthclaw-local"><img src="https://agentmods.dev/badge/mcp/aks129/healthclawguardrails/healthclaw-local/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/aks129/healthclawguardrails/healthclaw-local"><img src="https://agentmods.dev/badge/mcp/aks129/healthclawguardrails/healthclaw-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
healthclaw-local 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 12d 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
{
"healthclaw-local": {
"type": "http",
"url": "http://localhost:3001/mcp",
"headers": {
"X-Tenant-ID": "desktop-demo"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 12d ago First seen · 9 lines scan A 26693af6ea34
healthclaw-local is an MCP server published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), 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 2026-08-30.
Other mcp servers, from other repositories
synthetic-health-data
Privacy-preserving synthetic health data generation. FHIR R4/R5 compliant. Remote server at mcp.k01.is.
mcp
Securely access and manage FHIR healthcare data stored in Medplum. Remote server at api.medplum.com.
fhir-mcp-server
A Model Context Protocol (MCP) server that provides seamless, standardized access to Fast Healthcare Interoperability Resources (FHIR) data from any compatible FHIR server. Designed for easy integration with AI tools, developer workflows, and healthcare applications, it enables natural language and programmatic…
hl7gen
MCP server "hl7gen" as configured in mwaseem75/hl7gen. Runs hl7gen.mcp_server with python.
last-ehr
FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes. Runs locally from the @lastehr/mcp npm package. Needs 4 environment variables to run.
practice-fusion-mcp
FHIR-first, read-only MCP server for Practice Fusion. Runs locally from the practice-fusion-mcp npm package. Needs 7 environment variables to run.