Skip to main content
This page documents every tool exposed by the Panguard MCP server. Each tool includes its description, input schema, and example usage.

​
panguard_scan

Run a security health check scan on the local system. Returns risk score (0—100), grade (A—F), and list of security findings.
​
string
default:"quick"
Scan depth: quick (~30 seconds) or full (~60 seconds).
​
string
default:"en"
Output language: en or zh-TW.
Example prompt: “Run a full security scan on this machine in Chinese.” Example response: Risk score 72/100 (Grade C), 8 findings (1 critical, 2 high, 3 medium, 2 low).

​
panguard_scan_code

Scan a source code directory for security vulnerabilities (SAST). Detects SQL injection, XSS, hardcoded secrets, command injection, and more.
​
string
required
Source code directory to scan. Absolute or relative path.
​
string
default:"en"
Output language: en or zh-TW.
Example prompt: “Check the ./src directory for security vulnerabilities.”

​
panguard_guard_start

Start the Panguard Guard real-time threat monitoring daemon.
​
string
Data directory path. Defaults to ~/.panguard-guard.
​
string
Operating mode: learning or protection.
Example prompt: “Start real-time protection in learning mode.”

​
panguard_guard_stop

Stop the Panguard Guard daemon.
​
string
Data directory path. Defaults to ~/.panguard-guard.
Example prompt: “Stop the Guard engine.”

​
panguard_status

Get the current status of all Panguard services (Guard, Scan, Manager). Returns running state, threat counts, and system information.
​
string
Data directory path. Defaults to ~/.panguard-guard.
Example prompt: “What is the current security status of this machine?” Returns: Guard running state, mode, uptime, security score, active threats, events processed.

​
panguard_alerts

Get recent security alerts detected by Panguard Guard. Returns the latest threat events with severity and details.
​
number
default:"20"
Maximum number of alerts to return.
​
string
default:"all"
Filter by severity: critical, high, medium, low, or all.
​
string
Data directory path. Defaults to ~/.panguard-guard.
Example prompt: “Show me the last 5 critical alerts.”

​
panguard_block_ip

Manually block an IP address from accessing the system.
​
string
required
IP address to block (IPv4 or IPv6).
​
string
default:"1h"
Block duration. Examples: 1h, 24h, permanent.
​
string
Reason for blocking (stored in the action manifest).
Example prompt: “Block IP 203.0.113.50 for 24 hours because it was port scanning.”

​
panguard_generate_report

Generate a PDF compliance report from scan results. Returns the path to the generated PDF.
​
string
default:"./panguard-report.pdf"
Output PDF file path.
​
string
default:"en"
Report language: en or zh-TW.
​
string
default:"full"
Scan depth for the underlying scan: quick or full.
Example prompt: “Generate a PDF security report in Traditional Chinese.”

​
panguard_init

Initialize Panguard configuration with defaults (non-interactive mode).
​
string
Data directory path. Defaults to ~/.panguard-guard.
​
string
default:"en"
Default language: en or zh-TW.
​
string
default:"learning"
Initial operating mode: learning or protection.
Example prompt: “Initialize Panguard with Chinese language defaults.”

​
panguard_audit_skill

Audit an OpenClaw/AgentSkills SKILL.md directory for security issues. Checks manifest validity, prompt injection, tool poisoning, code vulnerabilities, dependencies, and permissions.
​
string
required
Path to skill directory containing SKILL.md.
Returns: Risk score (0—100) and detailed findings covering:
  • Manifest validity
  • Prompt injection detection
  • Tool poisoning analysis
  • Code vulnerability scanning
  • Dependency audit
  • Permission review
Example prompt: “Audit the skill at ./my-agent-skill for security issues.”

​
panguard_deploy

Deploy Panguard services: scan for vulnerabilities, start Guard monitoring, and generate an initial report. This is the one-click setup for full protection.
​
string
Data directory path. Defaults to ~/.panguard-guard.
​
string
default:"en"
Language: en or zh-TW.
​
string
default:"learning"
Initial Guard mode: learning or protection.
​
boolean
default:"true"
Whether to generate a PDF report after scanning.
Example prompt: “Deploy full protection on this machine with a PDF report.” Executes: panguard scan + panguard guard start + panguard scan --output report.pdf

​
Tool Availability

All tools are available to everyone. Panguard is 100% open source under the MIT license.
All tools return structured JSON responses that AI assistants can parse and present in natural language. The isError field in the response indicates whether the operation succeeded or failed.