Server data from the Official MCP Registry
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
infraveil-guard is a well-architected safety gate for AI agents with strong security fundamentals. The codebase is clean, readable stdlib-only Python with proper separation between agent and human approval paths (preventing agent self-approval), cryptographically sound approval code generation, and a tamper-evident ledger. No credentials are hardcoded, no dangerous exfiltration patterns exist, and permissions are appropriately scoped to the tool's purpose. Minor issues around input validation and error handling do not significantly impact the overall security posture. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
7 files analyzed · 9 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: INFRAVEIL_GUARD_THRESHOLD
Environment variable: INFRAVEIL_GUARD_MODE
Environment variable: INFRAVEIL_GUARD_HOME
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-infraveilhq-agent-guard": {
"env": {
"INFRAVEIL_GUARD_HOME": "your-infraveil-guard-home-here",
"INFRAVEIL_GUARD_MODE": "your-infraveil-guard-mode-here",
"INFRAVEIL_GUARD_THRESHOLD": "your-infraveil-guard-threshold-here"
},
"args": [
"infraveil-guard"
],
"command": "uvx"
}
}
}Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.