HOL Guard is a local security layer that reviews AI-agent actions before they run, including shell commands, file access, package installs, and MCP tool calls. AI-agent users use it to detect secret exposure, destructive operations, prompt injection, and supply-chain risks, then allow, block, or require approval according to policy. The catalogue contains skills, an MCP integration, a plugin, and an instruction for using it.
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/hashgraph-online/hol-guardWrote 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/hashgraph-online/hol-guard/input-hol-guard)<a href="https://agentmods.dev/mcp/hashgraph-online/hol-guard/input-hol-guard"><img src="https://agentmods.dev/badge/mcp/hashgraph-online/hol-guard/input-hol-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/hashgraph-online/hol-guard/input-hol-guard"><img src="https://agentmods.dev/badge/mcp/hashgraph-online/hol-guard/input-hol-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
hol-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 3d 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
{
"hol-guard": {
"command": "uvx",
"args": [
"hol-guard"
],
"env": {}
}
}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.
- 3d ago First seen · 9 lines scan A 5885e20d5b43
hol-guard is an MCP server published in the GitHub repository hashgraph-online/hol-guard (1,002 stars, last pushed today), licensed Apache-2.0. 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 2026-10-25.
Other mcp servers, from other repositories
node9
Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call. Runs locally from the node9-ai npm package.
filesystem
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.
shell
MCP server "shell" as configured in opena2a-org/hackmyagent. Runs locally from the @anthropic/mcp-shell-server npm package.
sunglasses
MCP server "sunglasses" as configured in sunglasses-dev/sunglasses. Runs sunglasses.mcp with python3.
ai-appsec
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC. Runs locally from the ai-appsec npm package.
mcpsafetywarden
MCP proxy server with behavioral profiling, security scanning, risk gating, and safe execution. Runs locally from the mcpsafetywarden Python package.