trackmcp
Back to directory

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

22 stars PythonOthers Updated Sep 4, 2026
agent-safetyai-agentsautomationguardrailshuman-in-the-loopmcppolicy-enginetool-use

No README could be loaded. View the project on GitHub for full documentation.

Frequently asked questions

What is intaris?

intaris is Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

How do I install intaris?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is intaris open source?

Yes — it is hosted on GitHub at https://github.com/fpytloun/intaris and has 22 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP