The directory of tools for agents

Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.

Read-only evidence for the tools agents run: MCP server records, coverage and policy.

Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.

Live data on AI agents, APIs and models: prices, free tiers, limits, outages, real-world usage.

Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.

Run Codex and Claude Code on your computer from an MCP client, and track or continue their runs.

Scan any website for AI agent readiness, payment protocols, and discovery endpoints

Security scanning and trust verification for AI agent tools.

Yes/no questions about local files, and relevant-file search, with TypeSafe Jev

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

Network-egress firewall for agent tools: check URLs against a declarative policy.

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.