• EXECUTION
  • MONITORING
  • VISIBILITY
  • HUMAN

How to run penetration tests with your AI

Connect Beagle Security to your AI client to manage security scanning through chat. You'll move from natural language requests to active vulnerability testing.

Ask AI about this page

Short answer

How can I run penetration tests using my AI?

You tell your AI client to start a scan on a specific target, and it uses the Beagle Security tools to trigger the test and track its progress. This lets you manage security testing without leaving your chat interface. You get real-time status updates and a clear view of active scans.

Scan outcomes.

Security testing results.

The AI handles the execution and monitoring so you can focus on the results.

EXECUTION

Automated scan triggers

The AI initiates the security testing process on your web apps or APIs. It translates your intent into active scan commands.

MONITORING

Real-time status tracking

Your agent keeps tabs on every active test. You'll know exactly when a scan is running or when it finishes.

VISIBILITY

Active test oversight

The AI pulls a list of all currently running tests. This gives you a snapshot of your security testing workload.

HUMAN

Manual remediation

The AI identifies the testing state, but you decide how to fix the vulnerabilities found. Security patching remains your responsibility.

The workflow

What your AI does when <the thing arrives>.

The AI acts as the bridge between your chat window and the Beagle Security testing engine.

  1. Initiate the scan

    When you ask to test a target, the AI sends the command to begin the security assessment.

    start_test

  2. Check progress

    The AI checks the current state of a specific test to see if it's still running or completed.

    get_test_status

  3. List active work

    The AI retrieves a list of all tests currently in progress to give you an overview.

    get_running_tests

  4. Report status

    The AI summarizes the testing data into plain text so you can understand the scan's current stage.

    get_test_status

Try it

Copy these to start.

Use these prompts to kick off your security testing.

Starting points

These are starting points. Replace the target URLs and API endpoints with your actual application addresses.

Beagle Security Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_U74zi3dTl0NmcQavuzksqiZA4T8DTVjFoQbausJC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Beagle Security capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "beagle-security-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_U74zi3dTl0NmcQavuzksqiZA4T8DTVjFoQbausJC/mcp"
    }
  }
}
Copy into chat04

  • Start a new penetration test on https://api.myapp.com

  • What is the status of the scan I just started on my web app?

  • Show me all the tests currently running in Beagle Security.

  • Check if the security test for my production API is finished yet.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Beagle Security once, then ask.

One connection links your AI client to the Beagle Security tools. Your credentials stay encrypted and secure.

Connect Beagle Security to your AI

FAQ

How this task behaves.

  • 01

    Can the AI fix the vulnerabilities it finds?

    No. The AI can only trigger and monitor the tests. You must manually apply any security patches or code changes.

  • 02

    Can the AI delete my existing security tests?

    No. The available tools only allow for starting tests, checking status, and listing running tests. Deletion is not supported.

  • 03

    How does the AI know which test is which?

    The AI uses the unique identifiers provided by the Beagle Security tools to track and report on specific scans.

  • 04

    Can I run tests on any URL?

    You can request a test on any target, but the scan will only execute if the target is valid and reachable by Beagle Security.

  • 05

    Does the AI handle the actual scanning engine?

    No. The AI sends the instructions to Beagle Security, which performs the actual heavy lifting of the penetration test.

  • More questions about Beagle Security? The Connector page answers them. See everything the Beagle Security Connector can do

Connect Beagle Security to Claude, Cursor, ChatGPT & more