hol-guard — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by hashgraph-online · MCP Server · ★ 451

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is hol-guard safe to install? View the security audit →

About hol-guard

HOL Guard [](https://scorecard.dev/vie

agent-securityai-agent-securityai-agentsai-antivirusai-securityclaude-codecodexcursordevsecopsdsh-plugin

Quick Facts

Stars451
Forks13
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score69.5548084104075/100
Open Issues34
Last Updated2026-08-19
Created2026-03-28
Platformsclaude-code, cli, codex, gemini, mcp, python
Est. Tokens~22k

Compatible Skills

These tools work well together with hol-guard for enhanced workflows:

  • agentrules-architect — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • awesome-claude-plugins — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • turbo — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • claude_codex_bridge — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • skill-scanner — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)

hol-guard alternative? Top 6 similar tools

Looking for a hol-guard alternative? If you're comparing hol-guard with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agent-security-scanner-mcp by sinewaveai · ⭐ 120

    Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (

  • nono by always-further · ⭐ 2.2k

    nono - a capability-based, multiplexing sandbox tool, built for developers - lift'n'shift seamless path to pro

  • shellward by jnMetaCode · ⭐ 129

    AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先

  • mcp-audit by apisec-inc · ⭐ 153

    See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate

  • memorix by AVIDS2 · ⭐ 662

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • Adrian by secureagentics · ⭐ 542

    Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, pro

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is hol-guard?

hol-guard is Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.. It is categorized as a MCP Server with 451 GitHub stars.

What programming language is hol-guard written in?

hol-guard is primarily written in Python. It covers topics such as agent-security, ai-agent-security, ai-agents.

How do I install or use hol-guard?

You can find installation instructions and usage details in the hol-guard GitHub repository at github.com/hashgraph-online/hol-guard. The project has 451 stars and 13 forks, indicating an active community.

What license does hol-guard use?

hol-guard is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to hol-guard?

The top alternatives to hol-guard on Agent Skills Hub include agent-security-scanner-mcp, nono, shellward. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools