New: CheckVibe MCP server — scan from Claude Code and Cursor nativelyRead the docs
Set a project up once. We re-scan on a schedule, diff against the last clean state, and only alert when something regresses. No noise. No daily emails about the same finding.
A URL is enough. Optionally connect the GitHub repo for code-level grounding.
Daily on Starter, hourly on Pro. Triggered on deploy if you wire up the GitHub or Vercel integration.
Every run is compared against your last clean snapshot. We surface what changed — not what is still there.
Slack, email, webhook. Severity-thresholded. Snooze rules per finding type so the channel stays signal-rich.
Daily for early projects, hourly for production, on-deploy for teams shipping multiple times a day.
Pick one or all three. Webhooks ship the full finding payload, ready for your alerting pipeline.
See exactly what regressed since last week — including dismissed-then-returned findings.
Mark a finding as accepted risk and it stays out of every future report — across the whole project.
Paste any URL — production app, staging build, vibe-coded prototype.
Every CheckVibe finding ships with a copy-paste prompt engineered for Claude, Cursor, and Windsurf — context, file paths, the exact diff.
Watch the traffic hitting your live app, classify suspicious patterns, and surface real threats — credential stuffing, scraping, prompt-injection probes — without flooding your inbox with noise.
Branded, executive-style PDFs and shareable dashboards for stakeholders, clients, and security reviewers — without writing a single sentence yourself.
Plug CheckVibe into Claude Desktop, Cursor, or any MCP-compatible client.
