# Beagle Security MCP for AI Agents AI Agent Connect > Beagle Security MCP for AI Agents. Scan your web applications for vulnerabilities, generate penetration test reports, and strengthen your security posture proactively. Stop manually hunting through vulnerability reports and start triggering high-fidelity security scans with plain English commands. Connect your Beagle Security account to your AI client to take full control of your automated cybersecurity audits and web application penetration testing through natural conversation. ## Overview - **Category:** fort-knox - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_U74zi3dTl0NmcQavuzksqiZA4T8DTVjFoQbausJC/ai-agent-connect - **Tags:** penetration-testing, cybersecurity, api-security, web-application-security, automated-audits, vulnerability-management ## Description Managing web application security usually feels like a chore of jumping between browser tabs, hunting for the right project, and squinting at fragmented reports. You have to remember which tests are running, which ones finished, and where the latest JSON data is hidden. This Connector changes that by bringing your Beagle Security audit infrastructure directly into your chat interface. Instead of manual toggling, you can just tell your agent to kick off a new penetration test or ask for a summary of the latest threats. It turns your AI into a dedicated security coordinator that handles the heavy lifting of orchestration. When you use this through the Vinkius catalog, you're moving away from being a dashboard operator and toward being a security strategist. You get a clear view of your audit infrastructure and the ability to pull high-fidelity results exactly when you need them, without the friction of manual data entry. This means you can spend less time on the logistics of running scans and more time actually fixing the vulnerabilities that matter. It bridges the gap between your security platform and your daily workspace, making it easier to stay on top of your security posture without the usual overhead. ## Tools ### get_application See the specific details of your currently selected application. This helps you confirm which endpoint the agent is targeting. ### get_running_tests List every security test that is currently active in your account. Use this to keep track of multiple concurrent scans without checking a dashboard. ### get_test_result Retrieve the full results of a completed test in JSON format. You can use this data to feed into other tools or for deep-dive analysis. ### get_test_sessions View a complete history of all previous test sessions. This is useful for tracking security trends over time. ### get_test_status Get the current progress and status of a specific security test. Use this to see if a scan is still running or has finished. ### list_applications Get a full list of all applications configured in your account. This helps you manage your audit infrastructure and see what's being monitored. ### list_projects See all the security projects you have organized. This allows you to quickly switch between different environments or client setups. ### start_test Trigger a new penetration test for a specific web application or API. This lets you start high-fidelity security audits using natural language. ### stop_test Immediately halt a running security test. Use this if you need to pause a scan to investigate a finding or clear a network issue. ## Prompt Examples **Prompt:** ``` List all security applications configured in my Beagle account. ``` **Response:** ``` I've retrieved your application directory. You currently have 3 configured endpoints, including 'Main Website' and 'API v1'. Would you like to check the last test session for any of them? ``` **Prompt:** ``` Start a new penetration test for the current application. ``` **Response:** ``` Security audit triggered! I've initiated a new high-fidelity penetration test for your application. The test is now running in the cloud. I'll monitor the progress and notify you of any critical threats. ``` **Prompt:** ``` What is the status of the current security test? ``` **Response:** ``` Fetching status... The current test is 'In Progress' (45% complete). So far, I've identified 2 low-risk items and 0 critical vulnerabilities. Shall I retrieve the real-time activity logs? ``` ## Capabilities ### Kick off penetration tests Trigger high-fidelity security scans for your web apps and APIs instantly. ### Monitor live test progress See exactly what a security scan is doing in real time. ### Pull vulnerability data Grab full test results in JSON format for your own analysis. ### Manage security projects View and organize your entire directory of applications and audit projects. ### Halt active scans Stop a running security test immediately if you need to pivot. ## Use Cases ### Post-deployment checks A DevOps engineer asks the agent to start a test for a new API endpoint to check for vulnerabilities immediately after a push. ### Rapid audit summaries A security lead asks for the results of the last test session to see if any critical threats were identified during the night. ### Infrastructure cleanup A security admin uses the agent to list all current projects to see which applications are still being monitored. ### Real-time monitoring An engineer asks for the status of a running test to see if the scan has reached the database layer yet. ## Benefits - Faster test execution: Use `start_test` to trigger scans for your APIs and web apps without navigating the Beagle dashboard. - Real-time oversight: Use `get_test_status` and `get_running_tests` to see exactly what's happening during a live security audit. - Instant data access: Use `get_test_result` to pull full JSON reports directly into your workspace for immediate analysis. - Organized audit infrastructure: Use `list_projects` and `list_applications` to keep your security targets organized in one place. - Simplified management: Use `stop_test` to kill a running scan the moment you need to change your testing strategy. ## How It Works The bottom line is you get a conversational interface for your entire security audit workflow. 1. Subscribe to the Beagle Security MCP in the Vinkius marketplace. 2. Grab your Access and Application tokens from the Beagle Security dashboard. 3. Connect your tokens to your AI client to start running audits. ## Frequently Asked Questions **Can I use Beagle Security MCP to run penetration tests?** Yes, you can trigger high-fidelity scans for your web applications and APIs using natural language. Your agent handles the communication with the Beagle platform to start, stop, and monitor your security audits. **How do I get vulnerability reports from Beagle Security?** You can ask your agent to pull the full results of any test session. It will retrieve the data in JSON format so you can analyze the specific threats identified during the scan. **Can the Beagle Security MCP monitor tests in real time?** Yes, you can ask your agent for the current status of any running test. It will provide updates on the progress percentage and any critical threats identified so far. **Is Beagle Security MCP good for API security?** It's a great fit for API security because it can specifically target your configured API endpoints. You can trigger tests and retrieve results to ensure your backend is protected against common vulnerabilities. **Can I manage multiple projects with Beagle Security?** Yes, the Connector allows you to list and manage all your security projects and applications. This makes it easy to keep your entire audit infrastructure organized within your AI workspace. **Does Beagle Security MCP work with Claude or Cursor?** It works with any MCP-compatible client, including Claude, Cursor, and Windsurf. You just connect your Beagle tokens and start managing your security audits through your preferred editor or chat interface. **How do I find my Beagle Access and Application Tokens?** Log in to Beagle Security. find the Access Token in your profile/user settings, and the Application Token in the settings of the specific project you want to test. **Can I stop a running test via AI?** Yes! The `stop_test` tool allows your agent to immediately terminate an active penetration test for the configured application. **How do I retrieve the vulnerability report?** First use `get_test_sessions` to identify the test's `resultToken`, then pass that token to `get_test_result` to retrieve the high-fidelity JSON report.