Sentinel MCP Server

MCP server for the Sentinel platform. Detect deepfakes, AI-generated images, and analyze faces — directly from Claude Desktop, Cursor, VS Code, or any MCP-compatible client.

Get your API key at app.scam.ai.

Setup

Install globally:

npm install -g sentinel-mcp-server

Then add to your MCP client config:

Edit claude_desktop_config.json:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sentinel": {
      "command": "sentinel-mcp-server",
      "env": {
        "SENTINEL_API_KEY": "sk_your-api-key"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "sentinel": {
      "command": "sentinel-mcp-server",
      "env": {
        "SENTINEL_API_KEY": "sk_your-api-key"
      }
    }
  }
}

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "sentinel": {
      "command": "sentinel-mcp-server",
      "env": {
        "SENTINEL_API_KEY": "sk_your-api-key"
      }
    }
  }
}

Tools

| Tool | What it does | |---|---| | sentinel_faceswap_detect | Detect face manipulation — swaps, de-aging, reenactment | | sentinel_ai_image_detect | Detect fully AI-generated images (DALL-E, Midjourney, SD, etc.) | | sentinel_face_analyze | Face age estimation and liveness/spoof detection | | sentinel_detection_history | View your past detection results | | sentinel_dashboard_stats | Usage statistics and analytics | | sentinel_usage_info | Credit balance and subscription info | | sentinel_task_status | Check status of async detection tasks |

Diagnostics

sentinel-mcp-diagnose

Checks Node.js version, server version, recent logs, and backend connectivity.

License

MIT