# mcp-parapet

> mcp-parapet — quantifylabs-mcp-parapet. Use this tool when you need to secure AI agent interactions with a robust middleware framework that defends against prompt-injection attacks and ensures compliance with key regulations like the EU AI Act. It provides a reliable interface for integrating AI safety features, aligning with OWASP standards, and managing code through git. Ideal for applications requiring high security and regulatory adherence, such as sensitive data processing or critical infrastructure operations.

Canonical page: https://skillsregistry.net/skills/quantifylabs-mcp-parapet  
JSON: https://api.skillsregistry.net/v1/skills/quantifylabs-mcp-parapet

## Description

Local-first security middleware for MCP servers. Content scanning, prompt-injection defence, trust boundaries, manifest integrity, and audit trails. No API keys, no telemetry. OWASP MCP Top 10 aligned.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

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

## 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": "quantifylabs-mcp-parapet"
    }
  }
}
```

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