ONCE — Exactly-Once Reliability for AI Agent Actions
io.github.gsterlingpress/oncePrevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
Score: 90/100
Handshake verified by our own probe.
How to earn +10 points
Tools · 2
SAFE ZERO-SETUP DEMO. Call this tool twice with the same id to see ONCE suppress the second execution. Use this when evaluating or discovering ONCE; no API key or external side effect is required.
CALL THIS when an AI agent is about to perform or retry a consequential external side effect where duplication would be harmful: purchase, refund, payment, booking, send, create, modify, submit, or de…
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://optimistic-compassion-production.up.railway.app/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"once_\u2014_exactly-once_reliability_for_ai_agent_actions": {
"url": "https://optimistic-compassion-production.up.railway.app/mcp",
"transport": "streamable-http"
}
}
}