# Beagle Security MCP for AI Agents AI Agent Connect > Beagle Security MCP lets you trigger, monitor, and retrieve results from automated penetration tests directly through your AI agent. It connects your security testing workflow to your chat interface so you can manage vulnerabilities without switching tabs. ## Overview - **Category:** developer-tools - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_GMZAD3cxpKBIjn1PzPSniqywLNWqPzzdh58BTIVy/ai-agent-connect - **Tags:** penetration-testing, web-security, automated-testing, vulnerability-assessment, security-audit ## Description This connector lets you pull your security testing data directly into your chat interface. You can ask your agent to list projects, check the status of a running scan, or grab a list of vulnerabilities without ever opening a separate dashboard. It turns a manual process into a conversation. You can trigger a new test for an application and then immediately ask for the results once it's done. This makes it much easier to stay on top of your security posture while you're actually writing code. By connecting this to the Vinkius catalog, you get a way to manage your penetration testing workflow in the same place you do your development work. It's about getting the facts you need in the moment you need them. ## Tools ### get_vulnerabilities List all the specific vulnerabilities found during a test. This gives you the raw data needed for remediation. ### list_applications See a list of all security applications in your account. Use this to get an overview of your protected assets. ### list_projects Get a list of all your security projects. This helps you navigate through different environments or targets. ### get_application_details Pull specific data about a security application. This helps you quickly verify application configurations. ### get_project_details Get the specifics for a particular security project. Use this to see which targets are included in a scan. ### get_test_results Grab the final results from a completed security test. This is how you see what the scanner actually found. ### get_test_status Check if a security test is still running, finished, or failed. It keeps you updated on active scans. ### get_user_profile Retrieve your Beagle account profile information. This is useful for verifying account permissions and details. ### start_test Trigger a brand new security test for an application. This starts the automated penetration testing process. ### stop_test Halt an active security test immediately. Use this if you need to pause a scan for any reason. ## Prompt Examples **Prompt:** ``` List all my security projects. ``` **Response:** ``` I've pulled your projects from Beagle Security. You have 4 active projects: - **E-commerce API** (ID: proj_123) - **Mobile Backend** (ID: proj_456) - **Admin Dashboard** (ID: proj_789) - **Auth Service** (ID: proj_999) Which one would you like to inspect? ``` **Prompt:** ``` Start a new security test for application app_998877. ``` **Response:** ``` Triggering the security test for app_998877 now... **Success!** Test ID `test_554433` has been started. You can check its progress using the status tool at any time. ``` **Prompt:** ``` Show me the findings from the last test test_554433. ``` **Response:** ``` Retrieving results for test_554433... I found 3 vulnerabilities: - **Critical**: SQL Injection - **High**: XSS - **Medium**: Missing Security Headers Would you like the full details for the SQL Injection? ``` ## Capabilities ### Trigger new security tests Start an automated penetration test for a specific application instantly. ### Check real-time test progress See if your current security scan is running, finished, or failed. ### Fetch lists of found vulnerabilities Pull a list of every security flaw found during a specific test. ### Manage security projects and applications View and organize all the targets and projects in your security account. ### Retrieve account profiles for auditing Get profile details and test histories for compliance and reporting. ## Use Cases ### The 'Is it safe?' check A developer wants to know if an API is clear. They ask the agent to check the results of the last scan for that app using `get_test_results`. ### The 'Status Update' A security lead wants to know if the nightly scan is done. They ask the agent to check the status of the latest project using `get_test_status`. ### The 'Quick Audit' An auditor needs a list of all projects. The agent pulls the project list using `list_projects` and exports it to the chat. ### The 'Emergency Stop' A test is running on a production-like environment and needs to pause. The user tells the agent to stop the active test using `stop_test`. ## Benefits - Stop context switching by using `list_projects` and `list_applications` to see your security landscape without leaving your editor. - Get instant updates on scan progress using `get_test_status` so you know exactly when your data is ready. - Pull critical flaws into your workspace immediately with `get_vulnerabilities` to prioritize your next bug fix. - Trigger new scans on demand with `start_test` to ensure your latest deployments are always checked. - Simplify compliance audits by quickly grabbing account data with `get_user_profile` and `get_project_details`. ## How It Works The bottom line is you get a direct line to your security testing data without leaving your primary workspace. 1. Subscribe to this Connector and provide your Personal Access Token and Application Token. 2. Connect the Connector to your preferred AI client like Claude, Cursor, or Windsurf. 3. Ask your agent to list projects, start tests, or pull vulnerability results into your chat. ## Frequently Asked Questions **What does the Beagle Security MCP do?** This Connector allows your AI agent to interact directly with your Beagle Security account. You can trigger penetration tests, check their status, and pull vulnerability results into your workspace. **Can I start a security scan with my AI agent?** Yes, you can use your agent to start new security tests for specific applications instantly without leaving your current tool. **How do I see my test results?** Your agent can fetch the final results of a completed test and summarize the findings for you, including the severity of each vulnerability. **Is this for manual security audits?** No, this is designed for automated penetration testing and vulnerability assessments. It works by interacting with the Beagle Security API. **Does it work with Cursor or Claude?** Yes, it works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code, through the Vinkius catalog. **How do I get my vulnerability data?** You can simply ask your agent to list the vulnerabilities for a specific test, and it will pull the data directly from your Beagle account. **Can I start a security test for a specific application from the agent?** Yes! Use the `start_test` action with your application's token. Your agent will trigger the penetration test in your Beagle Security account immediately. **How do I check if a running security test has finished?** Simply ask the agent to `get_test_status` with the Test ID. It will return the current phase of the test and its completion status. **Does the integration show me the details of found vulnerabilities?** Yes. Once a test is finished, you can use `get_vulnerabilities` or `get_test_results` to retrieve a list of findings, including severity and descriptions.