ONCE — Exactly-Once Reliability for AI Agent Actions MCP server
Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
0 stars
Reviews
Write oneNobody has reviewed ONCE — Exactly-Once Reliability for AI Agent Actions yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
ONCE — Exactly-Once Reliability for AI Agent Actions tools (2, 1 write)
write = sends, deletes, buys or postsonce_demoFreeSAFE 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.
once_executewrite actionFreeCALL 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 delete. ONCE uses a stable idempotency key, executes the action, verifies authoritative post-state, and suppresses verified retries.
Public scan report
scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 291ms20/20
- Tool poisoning2 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
- Maintenancelast push 6 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
Install directly
claude mcp add --transport http once https://optimistic-compassion-production.up.railway.app/mcp
ONCE — Exactly-Once Reliability for AI Agent Actions: common questions
- Is ONCE — Exactly-Once Reliability for AI Agent Actions MCP server safe?
- Mostly: it is graded B (79/100). Read the ONCE — Exactly-Once Reliability for AI Agent Actions safety report
- How do I install ONCE — Exactly-Once Reliability for AI Agent Actions?
- It runs remotely at optimistic-compassion-production.up.railway.app. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does ONCE — Exactly-Once Reliability for AI Agent Actions need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is ONCE — Exactly-Once Reliability for AI Agent Actions maintained?
- The last commit was 6 days ago (2026-09-13). The latest release is v0.8.4.
- Is ONCE — Exactly-Once Reliability for AI Agent Actions up?
- 100% of our last 2 checks got an answer. We check remote servers about four times a day.
- What can I use instead of ONCE — Exactly-Once Reliability for AI Agent Actions?
- Servers from other publishers that do the same job: Agent-Native Chat MCP server, MCP server and Ausca MCP server. Compare all ONCE — Exactly-Once Reliability for AI Agent Actions alternatives.
Alternatives to ONCE — Exactly-Once Reliability for AI Agent Actions
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- MCPAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
AuscaPay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.not reviewedEstablishedB
ProtectFail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.not reviewedGrowingC
LockstepDecision memory for AI coding agents: captures decisions once, briefs every agent before it acts.not reviewedGrowingA
