mcpbeat Sign in

ONCE — Exactly-Once Reliability for AI Agent Actions MCP Server

answering

ONCE — Exactly-Once Reliability for AI Agent Actions is answering right now. Last checked 11 min ago. It exposes 2 tools. Last commit 13 Sep 2026.

Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

Uptime history 68 days of history · worst day 99%
68 days agonow
100.0%
Uptime 24h
92 of 92 checks
2
Tools
read from the server
379 ms
Response time
average over 24h
0
Stars
last commit 13 Sep 2026

What changed 6

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 11 August 2026. No other catalogue keeps this.

13 Aug a tool changed version
11 Aug 2 tool descriptions were rewritten once_demo, once_execute
11 Aug 2 tools changed the parameters they ask for once_demo, once_execute
11 Aug a tool changed version

What the code does

We read the source, 3 d ago · tools taken from the live server · rules ccca72095570

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a file or shell call once_execute.idempotencyKey → src/once.js:65, once_execute.idempotencyKey → src/once.js:76
      return JSON.parse(await fs.readFile(this.receiptPath(key), 'utf8'));
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable src/auth.js:14
…,'usage');this.lock=new FileLock({locksDir:path.join(dataDir,'usage-locks')})}usagePath(keyId,period=monthKey()){return path.join(this.usageDir,keyId,`${period}.json`)}async get(keyId,period=monthKey()){return readJson(this.usagePath(keyId,period),{keyId,period,calls:0,verified:0…

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

run in your terminal
claude mcp add once --transport http https://optimistic-compassion-production.up.railway.app/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "once": {
      "url": "https://optimistic-compassion-production.up.railway.app/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.once]
url = "https://optimistic-compassion-production.up.railway.app/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "once": {
      "url": "https://optimistic-compassion-production.up.railway.app/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "once": {
      "url": "https://optimistic-compassion-production.up.railway.app/mcp"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

once
once_demo
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.
once_execute
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 delete. ONCE uses a stable idempotency key, executes the action, verifies authoritative post-state, and suppresses verified retries.

Endpoints

URLTransportStateLatencyChecked
https://optimistic-compassion-production.up.railway.app/mcp streamable-http answering 385 ms 11 min ago

Alternatives to ONCE — Exactly-Once Reliability for AI Agent Actions

same job, measured the same way
Safeagent
by azender1

Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.

185 installs/wk local only
TookEffect
by tookeffect

Independent effect verification and signed receipts for consequential AI agent actions.

answering
Creator Desk Agent Supervisor
by creatordeskai-prog

Agent completion verification with defects, corrections, and evidence receipts.

2 tools answering
InterAI Risk Oracle
by interailabs

Pre-execution policy gate for consequential agent actions with durable trust receipts.

9 tools answering
Kasbah MCP
by al-adnane

Governance layer for agentic AI — signed, verifiable receipts for every agent action.

30 installs/wk local only
HODLXXI Read-Only
by hodlxxi

Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification.

26 tools answering
EffectFence
by aurumflux20

Stops agents double-firing side effects: 1,000 racing duplicates, exactly one execution.

48 installs/wk local only
V
Vigil — an outside witness for AI agents
by vigilnotary

Agent leases, signed receipts, watchdogs, and optional paid source-verification evidence.

26 tools answering

ONCE — Exactly-Once Reliability for AI Agent Actions — questions

Answers built from our own checks of this server.

What can ONCE — Exactly-Once Reliability for AI Agent Actions do?
It exposes 2 tools, read directly from the server on our last check. Among them: once_demo, once_execute. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is ONCE — Exactly-Once Reliability for AI Agent Actions working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 379 ms. The bar chart above shows every period we have measured.
How do I connect ONCE — Exactly-Once Reliability for AI Agent Actions?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does ONCE — Exactly-Once Reliability for AI Agent Actions need an API key?
No. ONCE — Exactly-Once Reliability for AI Agent Actions completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is ONCE — Exactly-Once Reliability for AI Agent Actions?
It answers our handshake in 379 ms on average, which is faster than 34% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is ONCE — Exactly-Once Reliability for AI Agent Actions open source?
We cannot say either way: written in JavaScript, 0 stars on GitHub and 1 open issue, but we could not determine the licence, and without one the code is not open source by default.