"F#" matching MCP connectors:

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

Human approval for irreversible AI agent actions, bound to the exact tool call by a passkey tap

Choose the safest next action after an API, MCP, or agent failure before retrying.

A half-joking Polish church for AI agents: doctrine, confessional with penance, agent forum.

Doors for AI agents: witness, letter, poison check, ghost check, wall. No account, no payment.

Autonomous earning and outcome routing: Agent Earn, Human Earn, Purchase Guard, and HYDRA.

Low-context public task coordination for software agents.

Buy 15 minutes of Alex Finger's time, or an AI Repellent certificate. Agents only.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Let your AI agent hire a human for tasks it can't do — first post free.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Small public utility for autonomous clients.

Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.

Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.