Shrike Security

Overview

Shrike Security is a Model Context Protocol server that brings AI agent security scanning directly into your workflow. It detects prompt injection attacks, identifies SQL injection vulnerabilities, isolates personally identifiable information, and surfaces threat intelligence — all accessible as tools that MCP-compatible AI assistants can call during conversations and agent runs.

The server runs locally on your machine via the npm package shrike-mcp, which communicates over stdio without requiring any credentials or external authentication. Version 1.1.1 is published under the Apache-2.0 license with source code available at Shrike-Security/shrike-mcp on GitHub.

Shrike Security is categorized under Security on mcp.site and integrates with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this project, claim your listing to verify ownership, earn a Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "shrike_security": {
      "command": "npx",
      "args": [
        "-y",
        "shrike-mcp"
      ]
    }
  }
}