# ai.safe4/safe4

> ai.safe4/safe4 — ai-safe4-safe4. Use this tool when you need to validate an AI agent's purchasing decisions against its assigned tasks, ensuring alignment and accuracy. It solves problems of incorrect or unauthorized purchases by providing a verification mechanism. The tool accepts task assignments and purchase data as inputs and returns validation results, with payment made in USDC via x402.

Canonical page: https://skillsregistry.net/skills/ai-safe4-safe4  
JSON: https://api.skillsregistry.net/v1/skills/ai-safe4-safe4

## Description

Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.safe4%2Fsafe4)
- **Repository:** <https://github.com/Safe4AI/safe4-mcp>

## Use it

MCP endpoint published by the skill: `https://api.safe4.ai/mcp/`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ai-safe4-safe4"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-safe4-safe4` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-safe4-safe4/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt