HOL Guard
HOL Guard is an MCP server that adds developer tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. It has 1,109 GitHub stars, is released under the Apache-2.0 license and runs locally with uvx hol-guard.
github.com/hashgraph-online/hol-guard (opens in a new tab)
Data as of from the GitHub API and the official MCP registry; description from the project's repository. Report an error
Install HOL Guard
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"hol-guard": {
"command": "uvx",
"args": [
"hol-guard"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio hol-guard -- uvx hol-guardCursor
{
"mcpServers": {
"hol-guard": {
"type": "stdio",
"command": "uvx",
"args": [
"hol-guard"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"hol-guard": {
"type": "stdio",
"command": "uvx",
"args": [
"hol-guard"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
About HOL Guard
HOL Guard reviews agent actions before they run: shell commands, file access, package installs, and MCP tool calls. It detects secret exposure, destructive operations, prompt injection, and supply-chain risks, then allows, blocks, or requests approval according to your policy. It sees only the events each agent exposes to it: the support matrix lists, for each agent, the event surfaces Guard hooks and the actions it does not cover.
- mcp
- security
- agent-security
- ai-agent-security
- ai-agents
- ai-security
- claude-code
- cursor
- devsecops
- gemini-cli
Similar MCP servers
More developer tools MCP servers
SafeDep Vet MCP
safedep/vet
Protect your AI agents and IDEs from malicious open-source packages.
Active · last commit Nov 16, 2026
OfficialDeveloper toolsGopyscn
ludo-technologies/pyscn
Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
Active · last commit Nov 14, 2026
Developer toolsGoOpen Design
feimacode/open-design-agent-kit
Make posters, social posts, slides and landing pages with 198 design systems, checks and exports.
Too new to judge · created Sep 19, 2026
Developer toolsHTMLBuggregator MCP Server
buggregator/server
One local debugging server, one binary: catches errors, dumps, emails, logs, profiles and HTTP from your app in development.
Active · last commit Nov 11, 2026
OfficialDeveloper toolsGoLLM Sandbox
vndee/llm-sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
Active · last commit Nov 6, 2026
Developer toolsPythonInspo
Nutlope/inspo
Real production websites for coding agents: palettes, fonts, fold autopsies and reference JSX.
Maintained · last commit Oct 28, 2026
Developer toolsTypeScript
How do I install the HOL Guard MCP server?
Add the command uvx hol-guard to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is HOL Guard free?
The server is open source under the Apache-2.0 license, so running it is free. It does not declare any required API key.
Is HOL Guard actively maintained?
The most recent commit was on Nov 16, 2026. The latest release is v3.59.0, published Nov 4, 2026. appsgit only lists MCP servers with a commit in the last six months.