Guard Scanner is an MCP server published by koatora20 in the Agents category: 🛡️ Agent Security Scanner — 364 patterns, 35 threat categories, 27 runtime checks. Zero-Trust policy layer for MCP/A2A agents.
The repository has 2 stars and 0 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about Guard Scanner
Powered by Claude · Grounded in docs
I know everything about Guard Scanner. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v13.0.0v13.0.0 · 8 Mar 2026Full Changelog: https://github.com/koatora20/guard-scanner/compare/v9.1.0...v13.0.0
v9.1.0v9.1.0 · 5 Mar 2026Full Changelog: https://github.com/koatora20/guard-scanner/compare/v9.0.0...v9.1.0
v9.0.0v9.0.0 · 5 Mar 2026Full Changelog: https://github.com/koatora20/guard-scanner/compare/v8.0.0...v9.0.0
v8.0.0v8.0.0 · 5 Mar 2026Full Changelog: https://github.com/koatora20/guard-scanner/compare/v4.0.2...v8.0.0
v3.1.0v3.1.0 — OpenClaw Community Plugin + 3-Layer Runtime Defense · 22 Feb 2026What's New OpenClaw Community Plugin `openclaw.plugin.json` manifest with `before_tool_call` hook `openclaw plugins install guard-scanner` ready `configSchema` for mode/verbose/logDir settings 3-Layer Runtime Defense (19 patterns) Layer 1:…
No package has been published for this server, so install it from source: clone the repository and follow its README.
Is Guard Scanner safe to use with an AI agent?
Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.
Is Guard Scanner still maintained?
The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.