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/forever-healthy/AI4LWrote 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/forever-healthy/ai4l/d-pubmed)<a href="https://agentmods.dev/mcp/forever-healthy/ai4l/d-pubmed"><img src="https://agentmods.dev/badge/mcp/forever-healthy/ai4l/d-pubmed/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/forever-healthy/ai4l/d-pubmed"><img src="https://agentmods.dev/badge/mcp/forever-healthy/ai4l/d-pubmed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
d-pubmed 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 4d 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
{
"d-pubmed": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--network=host",
"-e",
"MCP_TRANSPORT_TYPE=stdio",
"-e",
"MCP_LOG_LEVEL=info",
"--env-file",
".env",
"ghcr.io/cyanheads/pubmed-mcp-server:latest"
]
}
}What else .mcp.json configures
This page is one entry in a file that holds 5. 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.
- 4d ago First seen · 19 lines scan A f3b39a82101a
d-pubmed is an MCP server published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 12d 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 2026-09-04.
Other mcp servers, from other repositories
phi-longevity-prism
Guideline-cited biomarker analysis for chronic conditions (diabetes, lupus, cancer). Synthetic. Runs locally from the @phi-longevity/mcp-server npm package.
ouramcp
Privacy-first, unofficial Oura MCP server for AI health, sleep, activity and heart-rate agents. Runs locally from the oura-mcp-unofficial npm package. Needs 8 environment variables to run.
nexonco-mcp
An advanced MCP Server for accessing and analyzing clinical evidence data, with flexible search options to support precision medicine and oncology research. Runs locally from the nexonco-mcp Python package.
oura-mcp
MCP server for Oura Ring data: sleep, readiness, HRV, resting heart rate. Runs locally from the my-oura-mcp Python package. Needs 8 environment variables to run.
fitness-tools
Deterministic fitness calculators — TDEE, adaptive TDEE, body fat, 1RM, macros — with consensus. Runs locally from the @almostjacked/fitness-tools-mcp npm package.
vitamind
MCP server for solar vitamin D: when the sun where you are can actually make vitamin D, for your skin type. Real solar geometry and live UV data. Runs locally from the vitamind-mcp npm package.