Skip to main content
Panguard MCP implements the Model Context Protocol standard, allowing AI assistants to interact with your security infrastructure through natural language. Ask your AI to scan for vulnerabilities, check guard status, block malicious IPs, or generate compliance reports — all through conversation.

​
Quick Start

Add Panguard to your AI assistant’s MCP configuration:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
  "mcpServers": {
    "panguard": {
      "command": "npx",
      "args": ["-y", "@panguard-ai/mcp"]
    }
  }
}
Restart Claude Desktop after saving.

​
What You Can Do

Once configured, interact with Panguard through natural language:
Example RequestMCP Tool Used
”Scan this machine for vulnerabilities”panguard_scan
”Check my source code for security issues”panguard_scan_code
”Start real-time protection”panguard_guard_start
”Stop the Guard engine”panguard_guard_stop
”What is the current security status?”panguard_status
”Show me recent alerts”panguard_alerts
”Block IP 203.0.113.50”panguard_block_ip
”Generate a PDF security report”panguard_generate_report
”Initialize Panguard configuration”panguard_init
”Audit this skill directory for security”panguard_audit_skill
”Deploy full protection on this machine”panguard_deploy

​
11 Available Tools

ToolCategoryDescription
panguard_scanScanRun a security health check scan (quick or full)
panguard_scan_codeScanSAST scan of source code directory
panguard_guard_startGuardStart the real-time monitoring daemon
panguard_guard_stopGuardStop the monitoring daemon
panguard_statusSystemGet status of all Panguard services
panguard_alertsGuardGet recent security alerts with severity filter
panguard_block_ipGuardManually block an IP address
panguard_generate_reportReportGenerate a PDF compliance report
panguard_initSystemInitialize Panguard configuration
panguard_audit_skillScanAudit an OpenClaw/AgentSkills directory
panguard_deploySystemOne-click deploy: scan + guard + report

Tools Reference

Full parameter reference and examples for all 11 MCP tools.

​
Architecture

AI Assistant (Claude Desktop, Cursor, etc.)
         |
    MCP Protocol (stdio transport)
         |
   Panguard MCP Server (@panguard-ai/mcp)
         |
   ┌─────┼─────┬──────┬───────┐
   Scan  Guard  Report  System
The MCP server runs as a local process, communicating with your AI assistant via stdio. All security operations execute locally on your machine — no data is sent to external servers through the MCP channel.

​
Prerequisites

  • Panguard CLI installed (panguard --version to verify)
  • Node.js 20+ (for npx execution)
  • A valid Panguard account (some tools require Solo plan or above)
The MCP server respects the same plan restrictions as the CLI. Tools that require a specific plan tier will return an appropriate error if your plan does not include that feature.