# mcpguard

> mcpguard — chenlaoshiyf-mcpguard. Use this tool when you need to detect and prevent security threats in AI agents, such as prompt injection, tool poisoning, and hidden instructions. MCPGuard scans local AI servers and skills to identify potential vulnerabilities, including homoglyphs, and provides outputs to help mitigate these risks. Ideal for use in development and deployment contexts where AI agent security is a concern.

Canonical page: https://skillsregistry.net/skills/chenlaoshiyf-mcpguard  
JSON: https://api.skillsregistry.net/v1/skills/chenlaoshiyf-mcpguard

## Description

Mingleng MCPGuard: local AI agent security scanner detecting prompt injection, tool poisoning, homoglyphs and hidden instructions in MCP servers and skills. 明棱，本地 AI 安全扫描器。

## Trust

- **Trust score (0–1):** 0.73
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/ChenLaoshiYF/mcpguard)

## 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": "chenlaoshiyf-mcpguard"
    }
  }
}
```

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