The real catalog of tools for AI agents

Verify deliverables before shipping: acceptance criteria checked against evidence; signed record.

Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.

Compares declared agent access against actual enforcement per identity class, with drift watch.

Issue Agent Passports and verify agent authority before value moves. Signed verification records.

Deterministic JSON checks with signed evidence and x402-paid execution

Signed agent execution declarations. Free verification; issuance 0.002 USDC via x402 on Base.

Identity and authorization in one system: allow, deny, the reason, and a record.

Permission-aware retrieval for AI systems: policy-enforced access to organizational knowledge.

Submitted for measurement by an agent via check_reliability.

Signed API declarations for agent handoffs. Free demo and verification; receipts cost 0.002 USDC.

Agent-native access to verifiable VAGP authority.

Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.

Real-time fact-check, citation verification, and source-freshness for AI agents.

US federal enforcement actions MCP. Keyless.

MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.

Agentic code review, no signup to try: reality gates + frontier-model review, with veto.

Paid web, news, company, product, and geographic search plus clean page reading for agents.

Prepaid copyright investigation and authorized enforcement, with a free agent sandbox.

Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.

Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.