rudimentall1/agent-guardrail

A deterministic policy firewall for AI agent tool calls. YAML rules, no LLM calls, no risk scores. CLI + MCP server (advisory) + @enforce() decorator (unbypassable). MIT, 46 tests, zero network dependency.

1Stars on the repository

1Mods indexed here, across every type

28d agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

agent-guardrail

rudimentall1/agent-guardrail

MCP server Claude CodeCodexCursor +2

A deterministic policy firewall for AI agent tool calls — blocks, warns, or allows based on rules you write, not a risk score. Runs locally from the guardrail-mcp Python package.

not rated 1 28d ago A tokens not measured original MIT