A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
Safe to build on. Strong signals across all dimensions.
Show users this server is actively trust-scored. Add the MCP Skills trust badge to your README to show current status.
kenryu42/cc-safety-net qualifies as Verified. Prove you own the repo and the badge is yours to embed in your README.
Claim with GitHub →We confirm ownership through GitHub (read-only) — we check that you can push to the repo. No fee, no email, no upsell.