Tool · agent-guardrailcloud costhosted
agent-chaperone
Apache-2.0 MCP proxy and Claude Code hooks adapter that screens an agent's tool calls before they run and tool results before it reads them against thresholds in a policy file; log-only by default, needs a TypeSafe API key.
Open upstream ↗Apache-2.0
Use responsibly
Deploys real cloud resources in your own account — this can cost money. Tear it down after use.
More tools
- dsh-jev-interceptoragent-guardrailMIT-licensed DeepSeek Harness plugin that scores non-read-only tool calls for risk, irreversibility and injection suspicion with TypeSafe's hosted Jev model, escalating or denying only in enforce mode; needs a paid API key.
- Jev Sentinelagent-guardrailMIT-licensed guard for coding agents (a Pi extension and Claude Code/Codex CLI plugins) that scores tool calls, outputs and replies with TypeSafe's Jev for injection and risk, then allows, asks, or blocks; needs a TypeSafe key.
- jev-guardagent-guardrailMIT-licensed hook for seven coding agents and any ACP pair that asks TypeSafe's hosted Jev typed questions about a tool call or its result, then denies, asks or allows it and flags suspected prompt injection; needs a billed key.
- AI Vuln Scannerdast/web-app-scannerA security research CLI that automates web-application vulnerability scanning with OWASP ZAP (spider + active attack) and uses the Anthropic Claude API to analyze findings and generate Markdown remediation reports. Ships an intentionally vulnerable Flask app as a safe test target.
- Aktoapi-securityOpen-source API-security platform with a large BOLA/IDOR/broken-auth test library, usable as an independent authorization cross-check.
- AmassreconDeep passive subdomain enumeration across many public sources.