A remote tool that prevents an AI agent from repeating an action that has already taken effect. It uses idempotency, verification, and saved receipts to track completed side effects.

Safely handling actions where duplicates would matter, while verifying results and keeping durable records of completed operations.

It reduces duplicate changes when an agent retries after a timeout, interruption, or uncertain result.

once — MCP server by GSterlingPress

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/gsterlingpress/once-api/once

Clone the repo

git clone --depth 1 https://github.com/GSterlingPress/once-api

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

once scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 6 lines

The source is not reproduced here

No licence file

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 6 lines scan A fc2dcab47f9f

Subscribe to this mod's changes

once is an MCP server published in the GitHub repository GSterlingPress/once-api (0 stars, last pushed 20d ago), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

once

Getting it into your agent

Grade A, and why

Nothing flagged

The source is not reproduced here

No licence file

What this file has done since we first saw it

Other mcp servers, from other repositories

agentkeeper-aria

airwallex-agentos

codex-in-claude

descartes-proxy

june-mcp

orchestrator