HOL Guard MCP Server

HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages, and MCP risks. Guard can allow safe work, block known threats, pause ambiguous actions for approval, and record security receipts for later review.

People connecting security tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-25 · ★ 470 · #2 OF 182 MAINTAINED SECURITY · VERIFIED 2026-08-25

Apache-2.0 · Python servers · how we verify → /methodology

01 · Install HOL Guard

Claude Code

claude mcp add hashgraph-online-hol-guard -- uvx hol-guard

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "hashgraph-online-hol-guard": {
      "command": "uvx",
      "args": [
        "hol-guard"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

pypi package hol-guard - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.hashgraph-online is GitHub-verified and matches the repo owner

03 · Who maintains HOL Guard

HOL Guard is maintained by hashgraph-online. We track 2 MCP servers from hashgraph-online - 2 actively maintained, 483 combined GitHub stars, oldest repo from Nov 2025. Full record: all servers from hashgraph-online.

  1. hashnet Universal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter ★ 13

04 · Facts

category
security - ranked #2 of 182 actively-maintained security servers as of 2026-08-25.
registry
io.github.hashgraph-online/hol-guard (active, first published 2026-08-16 · 78 versions)
packages
pypi:hol-guard

05 · HOL Guard FAQ

What is HOL Guard?

HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages, and MCP risks. Guard can allow safe work, block known threats, pause ambiguous actions for approval, and record security receipts for later review.

Is HOL Guard still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-25. We re-verify nightly.

How do I install HOL Guard?

Run `uvx hol-guard`. You can also paste the ready-made client config above.

Does HOL Guard run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

06 · Alternatives to HOL Guard

head to head · HOL Guard vs Snyk MCP Server · CrowdStrike Falcon MCP Server vs HOL Guard · Auth0 MCP Server vs HOL Guard

More security MCP servers · Coach Watts · Bug Bounty Intelligence · Honey Labs · Q Ring · IdentArk Gateway

More Python MCP servers · Ragstack · Bde Score · Computer-Use Agents API · Web Search · Agent Magnet · see all