# Pyrit-MCP

> Pyrit-MCP — ncasfl-pyrit-mcp. Use this tool when you need to leverage AI-powered red-teaming capabilities to identify potential risks and vulnerabilities in your systems. Pyrit-MCP solves problems related to threat detection and mitigation by providing a structured interface for LLMs like Claude to interact with Microsoft's PyRIT toolkit. It takes in MCP-compatible inputs and outputs structured threat intelligence, making it ideal for use cases that require real-time risk assessment and mitigation.

Canonical page: https://skillsregistry.net/skills/ncasfl-pyrit-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ncasfl-pyrit-mcp

## Description

An MCP (Model Context Protocol) server that wraps **Microsoft's PyRIT** (Python Risk Identification Toolkit), exposing its AI red-teaming capabilities as structured tools that Claude — or any MCP-compatible LLM — can orchestrate, direct, and reason about in real time.

## Trust

- **Trust score (0–1):** 0.75
- **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/ncasfl/Pyrit-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": "ncasfl-pyrit-mcp"
    }
  }
}
```

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