# Jadegate Scan

> Scan and audit installed MCP servers for security risks. Discovers servers from Claude Desktop, Cursor, Windsurf, Cline, Continue, and Zed configs, then assesses each for dangerous capabilities.

- Skill: `jadegate/jadegate-scan` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jadegate/jadegate-scan`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jadegate/jadegate-scan/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: jadegate (https://skillmd.com/u/jadegate)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jadegate/jadegate-scan

---


# MCP Security Scanner

Scan and audit installed MCP servers for security risks. Discovers servers from Claude Desktop, Cursor, Windsurf, Cline, Continue, and Zed configs, then assesses each for dangerous capabilities.

## When to Use

- User wants to audit their MCP servers for security risks
- User asks about MCP security or tool call safety
- User wants to know which MCP servers are installed and their risk level
- User mentions security scanning or server auditing

## Usage

```bash
jadegate scan                          # Scan all detected MCP servers
jadegate scan --output report.json     # Save JSON report
jadegate scan --probe                  # Launch servers to test capabilities
```

## What It Detects

- Shell execution capabilities (CRITICAL risk)
- Arbitrary code execution (CRITICAL risk)
- Browser automation (HIGH risk)
- Credential/secret access (HIGH risk)
- File system access (MEDIUM risk)
- Network capabilities (MEDIUM risk)

## Supported Clients

- Claude Desktop
- Cursor
- Windsurf
- Cline (VS Code)
- Continue
- Zed

## Output

Risk levels: CRITICAL, HIGH, MEDIUM, LOW for each detected MCP server.