A remote service that checks whether an AI agent’s purchase matches the task it was given. Each check is paid for in USDC, a digital currency, through the x402 payment system.

Checking an agent’s purchase decisions against its instructions through the Safe4 remote server.

It helps catch purchases that do not fit the requested task before they are accepted.

safe4 — MCP server for Claude Code and Codex by Safe4AI: A remote service that checks whether an AI agent’s…

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/safe4ai/safe4-mcp/safe4

Clone the repo

git clone --depth 1 https://github.com/Safe4AI/safe4-mcp

Made for: Claude Code, Codex, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/safe4ai/safe4-mcp/safe4.svg)](https://agentmods.dev/mcp/safe4ai/safe4-mcp/safe4)

Your own site

<a href="https://agentmods.dev/mcp/safe4ai/safe4-mcp/safe4"><img src="https://agentmods.dev/badge/mcp/safe4ai/safe4-mcp/safe4.svg" alt="Measured on agentmods" height="20"></a>

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 original No closer match found in the catalogue.

Security

Grade A, and why

safe4 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 4d 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

What it actually says

{
  "safe4": {
    "url": "https://api.safe4.ai/mcp/",
    "type": "streamable-http"
  }
}

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.

4d ago First seen · 6 lines scan A 99e25c378afa

Subscribe to this mod's changes

safe4 is an MCP server published in the GitHub repository Safe4AI/safe4-mcp (0 stars, last pushed 7d ago), licensed MIT. 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.

Security

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

reference-langchain

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

playwright-test

A high-level API to automate web browsers. Runs locally from the playwright npm package.

microsoft/playwright · not measured

supabase

Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.

supabase/supabase · not measured

mcp-search

MCP server "mcp-search" as configured in thedotmack/claude-mem. Runs const f=require('fs'),p=require('path'),o=require('os'),c=require('child_process');const h=o.homedir();const C=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude');const E=process.env.CLAUDE_PLUGIN_ROOT||process.env.PLUGIN_ROOT||'';const…

thedotmack/claude-mem · not measured

playwright

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

nextlevelbuilder/ui-ux-pro-max-skill · not measured