| What it does | Dead-man's switch for AI agents and automations
| Check your AI coding agent's config before it runs
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| GE
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 3 monitors, email alerts. Pro: $12/month with 25 monitors, Slack, Discord, Telegram alerts, and spend limits. Team: $39/month with 100 monitors, up to 10 people, same alerts and spend limits.
| Free browser scan available with no account. Paid plans: Individual $9/month (up to 1 developer), Team $49/month (up to 10 developers), Business $129/month (up to 50 developers). Enterprise plans available with custom quote.
|
|---|
| Key features | - Monitors AI agents, n8n flows, Make scenarios, Zapier zaps, Claude Code hooks, GitHub Actions, and Vercel crons
- Email alerts for silence and recovery on all plans
- Slack, Discord, and Telegram alerts on Pro and Team plans
- Runaway loop detection with spend limits
- 14-day ping history and charts
- Checks for missed pings every minute
- Grace period configuration
- Explicit failure pinging
- Encrypted webhook URLs and bot tokens
- Workspace collaboration on Team plan
| - Scans CLAUDE.md, .mcp.json, .claude/settings.json and related configuration files
- Detects risky permissions and allow rules such as Bash, * or bypassPermissions
- Flags hook commands that use the network, pipe into a shell or decode and run
- Identifies unpinned MCP packages and auto-confirm flags
- Identifies instructions to exfiltrate secrets
- Detects instructions that override or hide agent actions
- Runs in CLI, GitHub Actions, git hooks and browser
- Outputs findings in text, JSON or SARIF 2.1.0 format
- Compares git revisions with diff mode for pull request checks
|
|---|
| What makes it different | - Hosted service with no installation or scheduler setup required
- Alerts within about a minute of job failure
- Detects silent failures that don't throw errors
- Spending caps and baseline anomaly detection
- Built specifically for unattended overnight jobs and AI automations
| - Never executes code - reads files as text only
- Fixed deterministic rules that always give the same results
- Identifies real vulnerabilities like backdoored postmark-mcp and CVE-2025-6514 in mcp-remote
- Free browser scan requires no installation or account
- Works across multiple AI agent tools: Claude Code, Cursor, Codex and Gemini CLI
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 0 |
| Referring domains (Majestic) | 0 | 0 |