# mcp-shield

> mcp-shield — sophiacave-mcp-shield. Use this tool when you need to scan MCP servers for security vulnerabilities and ensure safe tool execution. It solves problems related to AI integration protection by detecting potential threats using 20 predefined rules. Input your MCP server details to receive output on detected vulnerabilities and security risks.

Canonical page: https://skillsregistry.net/skills/sophiacave-mcp-shield  
JSON: https://api.skillsregistry.net/v1/skills/sophiacave-mcp-shield

## Description

Security scanner for MCP servers. 20 rules, vulnerability detection, safe tool execution checks. Protect your AI integrations.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/sophiacave/mcp-shield)

## 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": "sophiacave-mcp-shield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sophiacave-mcp-shield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sophiacave-mcp-shield/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