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/Tianyu-Qu/mcp-pubmed-evidenceWrote 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/tianyu-qu/mcp-pubmed-evidence/pubmed-evidence)<a href="https://agentmods.dev/mcp/tianyu-qu/mcp-pubmed-evidence/pubmed-evidence"><img src="https://agentmods.dev/badge/mcp/tianyu-qu/mcp-pubmed-evidence/pubmed-evidence/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/tianyu-qu/mcp-pubmed-evidence/pubmed-evidence"><img src="https://agentmods.dev/badge/mcp/tianyu-qu/mcp-pubmed-evidence/pubmed-evidence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pubmed-evidence 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
{
"pubmed-evidence": {
"command": "python",
"args": [
"-m",
"mcp_pubmed_evidence.server"
],
"env": {
"PYTHONPATH": "/path/to/mcp-pubmed-evidence/src"
}
}
}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 · 12 lines scan A cd068abbefb0
pubmed-evidence is an MCP server published in the GitHub repository Tianyu-Qu/mcp-pubmed-evidence (2 stars, last pushed 2mo 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
pubmed
PubMed MCP — wraps the NCBI E-utilities API (biomedical literature, free, no auth). Remote server at gateway.pipeworx.io.
codex-control-plane-mcp
Durable MCP control plane for long-running Codex Desktop tasks. Runs locally from the codex-control-plane-mcp Python package.
find-research-papers-mcp
Search open-source research papers across arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar. Runs locally from the find-research-papers-mcp npm package. Needs 1 environment variable to run.
data-aggregator-mcp
Research-data acquisition MCP — find and fetch datasets across archives, omics registries, and literature. Runs locally from the data-aggregator-mcp Python package. Needs 12 environment variables to run.
cdc-health-mcp-server
Search and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk. Runs locally from the @cyanheads/cdc-health-mcp-server npm package. Needs 2 environment variables to run.
data-aggregator
Research-data acquisition MCP — find and fetch datasets across archives, omics registries, and literature. Runs locally from the data-aggregator-mcp Python package.