Deterministic policy enforcement and MCP management for AI agent tool calls.
Deterministic policy enforcement for AI agent tool calls. Every action an agent proposes passes through user-defined rules before execution. No LLM in the authorization path. Advisory nudges are separate from authorization. 25ms end-to-end. There is no npm or PyPI package for signet-eval. The public distribution path is crates.io plus source install from GitHub. The MCP Registry listing points at…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Deterministic policy enforcement for AI agent tool calls. Every action an agent proposes passes through user-defined rules before execution. No LLM in the authorization path. Advisory nudges are separate from authorization. 25ms end-to-end. There is no npm or PyPI package for signet-eval. The public distribution path is crates.io plus source install from GitHub. The MCP Registry listing points at the repository metadata; the runtime is the local stdio 1. Hook into Claude Code — add to : For…