# read-no-evil-mcp

> read-no-evil-mcp — thekie-read-no-evil-mcp. Use this tool when you need to protect AI agents from malicious email content, specifically prompt injection attacks. It serves as a secure email gateway, filtering out harmful inputs to ensure the agents' safety and integrity. By integrating with git, it provides a reliable and version-controlled solution for email security.

Canonical page: https://skillsregistry.net/skills/thekie-read-no-evil-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thekie-read-no-evil-mcp

## Description

A secure email gateway MCP server that protects AI agents from prompt injection attacks hidden in emails.

## Trust

- **Trust score (0–1):** 0.58
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** communication
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/thekie/read-no-evil-mcp)

## 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": "thekie-read-no-evil-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thekie-read-no-evil-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thekie-read-no-evil-mcp/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