Shrike MCP

🚀 Shrike MCP

9 security tools for AI agents. Multi - stage detection pipeline. One MCP server.

Shrike MCP offers real - time security scanning for AI agents, covering prompts, responses, SQL queries, file writes, CLI commands, and web searches. It can detect prompt injection, jailbreaks, PII leaks, and data exfiltration before they affect your users or systems.

🚀 Quick Start

1. Sign up at shrikesecurity.com/signup to obtain your API key.
2. Add to your MCP client config:

{
  "mcpServers": {
    "shrike - security": {
      "command": "npx",
      "args": ["-y", "shrike - mcp"],
      "env": {
        "SHRIKE_API_KEY": "your - api - key"
      }
    }
  }
}

3. Your agent now has 9 security tools. Every prompt, response, and tool call will be scanned through the full detection pipeline.

✨ Features

Nine Tools

How It Works

Shrike uses a scan - sandwich pattern. Every agent action is scanned on both sides:

User Input → scan_prompt → LLM Processing → scan_response → User Output
                              ↓
              Tool Call (SQL, File, Command, Search)
                              ↓
            scan_sql_query / scan_file_write / scan_command / scan_web_search
                              ↓
                       Tool Execution

Inbound scans detect injection attacks. Outbound scans detect data leaks. Tool - specific scans detect SQL injection, path traversal, command injection, and PII exposure. Flagged actions trigger human - in - the - loop approval via check_approval.

Detection Pipeline

Every scan runs through a multi - stage cascade, from sub - millisecond pattern matching to deep semantic analysis. So zero - day attacks that evade simple regex can still be caught by the LLM layer.

📦 Installation

Community Tier (Free)

Sign up at shrikesecurity.com/signup without approval or sales call.

Configuration

Environment Variables

Claude Desktop

{
  "mcpServers": {
    "shrike - security": {
      "command": "npx",
      "args": ["-y", "shrike - mcp"],
      "env": { "SHRIKE_API_KEY": "your - api - key" }
    }
  }
}

Cursor

Add to Cursor settings (.cursor/mcp.json):

{
  "mcpServers": {
    "shrike - security": {
      "command": "npx",
      "args": ["-y", "shrike - mcp"],
      "env": { "SHRIKE_API_KEY": "your - api - key" }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "shrike - security": {
      "command": "npx",
      "args": ["-y", "shrike - mcp"],
      "env": { "SHRIKE_API_KEY": "your - api - key" }
    }
  }
}

🔧 Technical Details

Security Model

This server implements a fail - closed security model:

• Network timeouts result in BLOCK (not allow).
• Backend errors result in BLOCK (not allow).
• Unknown content types result in BLOCK (not allow). This prevents bypass attacks via service disruption.

Response Format

Blocked:

{
  "blocked": true,
  "threat_type": "prompt_injection",
  "severity": "high",
  "confidence": "high",
  "guidance": "This prompt contains patterns consistent with instruction override attempts.",
  "request_id": "req_lxyz123_a8f3k2m9"
}

Safe:

{
  "blocked": false,
  "request_id": "req_lxyz123_a8f3k2m9"
}

📚 Documentation

Here are some useful links:

• Shrike Security — Sign up, dashboard, docs
• [GitHub](https://github.com/Shrike - Security/shrike - mcp) — Source code, issues
• [npm](https://www.npmjs.com/package/shrike - mcp) — Package registry
• MCP Registry — Search "shrike"

📄 License

This project is under the Apache License 2.0. See LICENSE for details.