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/liminalpepe/agent-guard-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/liminalpepe/agent-guard-mcp/agent-guard)<a href="https://agentmods.dev/mcp/liminalpepe/agent-guard-mcp/agent-guard"><img src="https://agentmods.dev/badge/mcp/liminalpepe/agent-guard-mcp/agent-guard/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/liminalpepe/agent-guard-mcp/agent-guard"><img src="https://agentmods.dev/badge/mcp/liminalpepe/agent-guard-mcp/agent-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-guard 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 1mo 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
{
"agent-guard": {
"command": "npx",
"args": [
"-y",
"@liminallablibs/[email protected]"
]
}
}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.
- 1mo ago First seen · 9 lines scan A 23d0e2971b40
agent-guard is an MCP server published in the GitHub repository liminalpepe/agent-guard-mcp (0 stars, last pushed 3mo 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
pkgxray
MCP server "pkgxray" as configured in adamsjack711-ux/pkgxray. Runs ./bin/mcp-server.js with node.
factreason
MCP server "factreason", hosted remotely at factreason.com, as configured in factreason/factreason.
dependency-compat-mcp
MCP server answering whether two exact package or runtime versions work together, with sources. Runs locally from the dependency-compat-mcp Python package.
skilltotal
AI Component Security Platform — static security analysis for AI components (CLI engine). Runs locally from the skilltotal Python package.
proof-of-commitment
Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals. Runs locally from the proof-of-commitment npm package.
megalinter
MCP server "megalinter" as configured in DownAtTheBottomOfTheMoleHole/megalinter-mcp. Runs ./dist/index.js with node.