Sentinel Scan

Overview

Sentinel Scan is an MCP security scanner that detects tool poisoning, prompt injection, and rug-pulls using 10 OWASP heuristics. By speaking the Model Context Protocol, it lets AI assistants call security checks as native tools rather than requiring manual data transfer between applications.

The server runs locally via the npm package sentinel-scan-cli, which communicates over stdio on your machine. No authentication is required—it works immediately after installation. The latest release is v1.4.16 under the MIT license, with source code available at Ventrova/sentinel-scan-cli on GitHub.

Sentinel Scan appears in the Security category on mcp.site and works with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. Maintainers from Ventrova can claim this listing to verify ownership, earn a Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "sentinel_scan": {
      "command": "npx",
      "args": [
        "-y",
        "sentinel-scan-cli"
      ]
    }
  }
}