Secretguard MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 13 Aug 2026.
Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
Today is the operative word: we check Secretguard MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
GitHub for AI agents — repos, files, code search, issues, PRs, commits. Read-only default.
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
The repo guardian AI agents handshake with before they touch your code.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Git hosting for AI agents: repos, changes, focused diffs, reviews, issues, code search.
Answers built from our own checks of this server.