• ACTIVE
  • MONITOR
  • CONTROL
  • HUMAN

How to run automated security tests with your AI

Connect Beagle Security to your agent to manage penetration tests. You can control the entire scanning process without leaving your chat interface.

Ask AI about this page

Short answer

How can I run security tests through my AI?

Your agent uses the Beagle Security MCP to trigger new penetration tests, check the progress of active scans, and kill any running tests immediately. You'll see how the agent handles each stage of a scan below.

Test outcomes

Where your security data lands.

The agent moves between these states based on your commands.

ACTIVE

Running scans

The agent starts a test and keeps track of its progress. You get real-time updates on whether the scan is still running or finished.

MONITOR

Status tracking

The agent checks the current state of your security tests. You can ask for updates whenever you need to know if a scan is complete.

CONTROL

Stopping tests

If a test is taking too long or you need to pivot, the agent stops the execution. This prevents unnecessary resource use.

HUMAN

Reviewing results

The agent manages the execution, but you decide how to handle the vulnerabilities found. You'll need to manually review the findings in Beagle Security.

The workflow

What your AI does when a test arrives.

The agent acts as the bridge between your chat and the Beagle Security engine.

  1. Initiate the scan

    The agent sends the command to begin a new penetration test on your target application.

    start_test

  2. Track progress

    The agent checks the backend to see if the security scan is still active or has reached a conclusion.

    get_test_status

  3. Halt execution

    If you need to cancel a scan, the agent sends the instruction to terminate the process immediately.

    stop_test

  4. Verify completion

    The agent uses the status tool to confirm the test has finished so you can move to the next task.

    get_test_status

Try it

Copy these to start.

Use these prompts to begin interacting with Beagle Security.

Starting points

These are basic commands. Replace the target names with your actual application URLs or test IDs.

Beagle Security Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_GMZAD3cxpKBIjn1PzPSniqywLNWqPzzdh58BTIVy/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-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_GMZAD3cxpKBIjn1PzPSniqywLNWqPzzdh58BTIVy/mcp"
    }
  }
}
Copy into chat04

  • Start a new penetration test for my web app at https://staging.example.com

  • What is the current status of the test I just started?

  • Stop the security test that is currently running on my production API

  • Check if the scan for my mobile backend has finished yet

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

Start here

Connect Beagle Security once, then ask.

Just link your account through Vinkius. Your credentials stay encrypted and you can start running tests through your agent immediately.

Connect Beagle Security to your AI

FAQ

How this task behaves.

  • 01

    Can my AI fix the vulnerabilities it finds?

    No. The agent can only start, monitor, and stop the tests. You must manually fix any security issues discovered.

  • 02

    Can the AI delete my test history?

    No. The available tools only allow for starting, checking, and stopping tests. Deleting records is not supported.

  • 03

    How do I know if a test is finished?

    You can ask your agent for the status of a specific test, and it will check the current state for you.

  • 04

    Can I run multiple tests at once?

    Yes, you can trigger new tests through your agent as needed.

  • 05

    Does the AI see my full security report?

    The agent uses the status tool to see if a test is running or done, but it does not pull the full vulnerability data into the chat.

  • 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