# Agent Safe

> Use this tool when you need to protect AI agents from email-based threats, such as phishing, prompt injection, and CEO fraud. Agent Safe detects and prevents these attacks, ensuring the security and integrity of AI interactions. It takes in email inputs and outputs threat detection results, making it an essential component in safeguarding AI systems.

Canonical page: https://skillsregistry.net/skills/agentsafe  
JSON: https://api.skillsregistry.net/v1/skills/agentsafe

## Description

Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentsafe)

## Use it

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": "agentsafe"
    }
  }
}
```

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