# MCP Shield

> MCP Shield — rob925-mcp-shield. Use this tool when you need to detect and prevent security vulnerabilities in MCP servers and AI agent projects. The MCP Shield scans for dangerous patterns such as leaked secrets, shell execution, and prompt-injection text, providing a secure interface for CI-friendly severity gates. It runs as both a CLI and MCP server, making it an ideal solution for identifying and mitigating potential security threats.

Canonical page: https://skillsregistry.net/skills/rob925-mcp-shield  
JSON: https://api.skillsregistry.net/v1/skills/rob925-mcp-shield

## Description

Security scanner and MCP server that catches dangerous patterns in MCP servers and AI agent projects, such as leaked secrets, shell execution, and prompt-injection text. Runs as both a CLI and MCP server with CI-friendly severity gates.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/eace2guq39)
- **Repository:** <https://github.com/rob925/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": "rob925-mcp-shield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rob925-mcp-shield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rob925-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