HOL Guard
Local-first security layer that reviews AI coding agents' shell commands, file access, package installs and MCP tool calls before they run.
Tags
Description
Install with pipx install hol-guard && hol-guard init. Guard hooks into the harness through native hooks, managed MCP proxies or launch integrations, and checks prompts and tool results as well as actions. It supports Codex, Claude Code, GitHub Copilot CLI, Cursor, Cline, Gemini CLI, OpenCode, OpenClaw, Hermes, Antigravity, Devin and others. Guard Local is open source (Apache-2.0, PyPI hol-guard, Python 3.10+). Guard Cloud is an optional paid service with Free, Solo, Pro and Team plans. The repo's server.json also declares a stdio MCP server (uvx hol-guard mcp serve --stdio). Latest release v3.58.0 (Oct 2026). Maintained by HOL; submitted via GitHub issue by a HOL-affiliated contributor.
Agent access
Related
- Claude Code: Anthropic's agentic coding tool that reads your codebase, edits files, runs commands and integrates with dev tools; available in terminal, IDE, desktop and browser.
- OpenAI Codex CLI: OpenAI's lightweight open-source coding agent that runs in your terminal.
- Cursor: AI code editor and coding agent with Agent mode, Rules, Skills, MCP servers and a CLI.
- Snyk Agent Scan: Security scanner that discovers agent components on your machine (agents, MCP servers, skills) and scans them for prompt injections and vulnerabilities.
Sources
- https://hol.org/guard
- https://github.com/hashgraph-online/hol-guard
- https://pypi.org/project/hol-guard/
- https://hol.org/guard/pricing
- https://github.com/hashgraph-online/hol-guard/blob/main/server.json
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)