Invariant Guardrails
Rule-based guardrails that sit between an agent and its MCP servers or LLM provider, checking and blocking tool calls and messages.
Tags
Description
Rules use a Python-like matching language that can follow flows between tool calls, e.g. block sending email to an unknown address after reading the inbox. It runs as an MCP or LLM proxy. From Invariant Labs (now part of Snyk), whose docs now sit under mcp-scan. Apache-2.0. Last PyPI release invariant-ai 0.3.5 (Jul 2025); last commit Jan 2026.
Related
- 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://github.com/invariantlabs-ai/invariant
- https://invariantlabs.ai
- https://invariantlabs-ai.github.io/docs/mcp-scan/guardrails-reference/
- https://pypi.org/project/invariant-ai/
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)