Categories › AI & Agents › Multi-agent, orchestration & workflows
Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
Remote server: your requests and data go to policy-gate.3labsio.workers.dev. Claude Code: claude mcp add --transport http policy-gate https://policy-gate.3labsio.workers.dev/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
policy_example — Free. Worked allow/require_approval/deny verdicts from the live policy engine, so you can judge the service before paying for it.policy_rules — Free. The full built-in policy: every tier, rule, condition and rationale. Nothing about how a verdict is reached is hidden.policy_check — Evaluate a proposed agent action against a policy and return allow / require_approval / deny with the matched rule and rationale. Paid per cfirst_42_sponsor — Pay Fieldproof $42. Returns every live rail: Stripe card_uri, EIP-681 usdc_uri, BIP-21 btc_uri, x402 POST /v1/sponsor, Zelle, and GET /v1/inNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.