# Agent Safe Message MCP

> Use this tool when you need to protect your AI agent from malicious messages, images, and videos across multiple platforms. The Agent Safe Message MCP suite scans and secures against phishing, BEC, malware, and manipulation, providing a safe and trusted environment for your agent to operate. It offers a range of tools, including a free triage tool for instant assessment and a feedback tool for improved detection.

Canonical page: https://skillsregistry.net/skills/agent-safe-email-agentsafeemail  
JSON: https://api.skillsregistry.net/v1/skills/agent-safe-email-agentsafeemail

## Description

A suite of MCP tools that scan every message, image, and video your AI agent handles.

Your AI agent processes messages across every platform — but should it trust them? Agent Safe is a 10-tool MCP security suite that protects against phishing, BEC, malware, and manipulation on any messaging platform your agent operates on. Start with the free triage tool to instantly know which checks to run, and use the free feedback tool to help improve detection.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-05-11

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/agent-safe-email/agentsafeemail)

## 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": "agent-safe-email-agentsafeemail"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agent-safe-email-agentsafeemail` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agent-safe-email-agentsafeemail/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