# BugBug MCP MCP > BugBug MCP lets you automate web application testing using natural conversation. Stop clicking through dashboards to find regressions. You connect this MCP to your AI agent and tell it exactly what tests to run, when they ran last, or if certain IPs need whitelisting for a deployment. It turns complex QA workflows into simple commands, letting you keep quality monitoring right inside your coding environment. ## Overview - **Category:** developer-tools - **Price:** Free - **Tags:** browser-automation, end-to-end-testing, no-code-testing, web-testing, quality-assurance, regression-testing ## Description You can take full control of your app's quality monitoring without ever leaving your IDE. This MCP connects BugBug’s automated browser testing engine directly to your AI agent. Instead of manually triggering tests or sifting through pages of run logs, you simply tell your agent what you need. For instance, you can ask it to check the status and results for a specific test run ID, or maybe list all projects available across your accounts. The MCP handles the complex back-end calls—like running an entire suite in the cloud programmatically and tracking its aggregate results in real time. This keeps QA oversight right where the code is written. When you subscribe to this MCP via Vinkius, your agent acts like a dedicated quality architect, allowing you to manage test execution and retrieve detailed reports using only natural language. ## Tools ### get_ips Retrieves a list of BugBug IP addresses for your network firewall settings. ### get_suite_run Checks the current status and results of a particular suite execution run. ### get_suite Gets specific details about an entire test suite by its ID. ### get_test_run Checks the status and results for a single test's run execution. ### get_test Gets detailed information about one specific, individual test case. ### list_projects Displays all the projects you have set up in BugBug. ### list_suite_runs Lists records of recent times when entire test suites were executed. ### list_suites Shows all the available, defined test suites for your applications. ### list_test_runs Lists records of recent times when individual tests were executed. ### list_tests Shows all the individual, defined test cases available in your system. ### run_suite Initiates an automated run for a specified test suite. ### run_test Starts an immediate, automated execution of a single defined test. ## Prompt Examples **Prompt:** ``` List all my automated tests in BugBug. ``` **Response:** ``` I've retrieved your test directory. You currently have 15 automated tests, including 'Login Flow' (ID: test_123) and 'Checkout Process'. Which one would you like to execute or inspect? ``` **Prompt:** ``` Run the 'Smoke Test' suite (ID: 'suite_456') in the 'Staging' environment. ``` **Response:** ``` Suite execution triggered! I've initiated the 'Smoke Test' suite in your staging environment. The run ID is 'run_789'. I'll monitor the progress and notify you as soon as the results are ready. ``` **Prompt:** ``` Show the status and results for the latest test run ID 'run_789'. ``` **Response:** ``` Fetching run results... Execution run_789 has successfully 'Passed'. All 5 steps were verified. You can view the full high-fidelity report here: [report_url]. Shall I check the historical trends for this test? ``` ## Capabilities ### Run Specific Tests You instruct the agent to execute a single named test immediately. ### Execute Full Test Suites The MCP triggers an entire grouping of related tests to run simultaneously and reports on the overall quality status. ### Check Historical Results You retrieve detailed performance reports and execution statuses for past test runs, helping spot trends or regressions. ### Manage Test Assets The agent lists all available projects, tests, or entire suites so you know what needs checking. ### Get Network Information You retrieve the necessary BugBug IP addresses for adding them to secure firewall allowlists. ## Use Cases ### The Release Candidate Check A developer is about to merge code for the checkout page. Instead of running a full, slow manual test cycle, they ask their agent, 'Run the Checkout Process suite.' The MCP uses `run_suite` and provides immediate status checks via `get_suite_run`, letting them know if critical paths passed before committing. ### The Security Audit Prep A DevOps engineer needs to harden the firewall for a staging environment. They ask their agent, 'What are the BugBug IP addresses?' The MCP calls `get_ips`, providing the exact list needed, eliminating manual lookups and copy-pasting. ### Investigating a Recent Failure A QA engineer notices an intermittent bug. They use the agent to check historical data by running 'Show me all test runs for the Login Flow.' The MCP uses `list_test_runs`, allowing them to pinpoint when and where the failure first occurred. ### Verifying Feature Parity A product manager wants to ensure a new feature works across all environments. They ask their agent, 'List all available test suites.' The MCP uses `list_suites`, giving them a complete directory they can then pass back to the agent for targeted execution. ## Benefits - You save time by not needing to manually trigger tests. Simply asking the agent to 'run a smoke test' executes the necessary workflow instantly. - The MCP gives you clear visibility into history and performance using `list_suite_runs` or `list_test_runs`, letting you programmatically track QA trends over time. - You can check current application status by running tests, whether it’s a single test via `run_test` or an entire grouping using `run_suite`. The agent reports the real-time outcome of both. - When preparing for deployment, you don't have to dig through documentation; use the MCP to retrieve necessary network data with `get_ips`, ensuring your firewall rules are correct. - You get instant diagnostic feedback. Instead of vague logs, running a test and checking its status with `get_test_run` gives precise results on every step. ## How It Works The bottom line is that setting up the connection gives your AI agent full, programmatic control over complex QA workflows. 1. First, subscribe to this MCP and grab your API Token from your BugBug account dashboard. 2. Next, connect that token in your AI agent via any compatible client. The connection establishes access to all the core testing tools. 3. Finally, you talk to your agent using natural language commands—like 'Run the login flow suite' or 'Show me the IPs for project X.' — and get instant results. ## Frequently Asked Questions **How do I list all my automated tests using BugBug MCP?** You use the `list_tests` tool. This command immediately pulls up a directory of every single test case you have defined in your system. **What if I need to run an entire set of tests for my project?** Use the `run_suite` tool. You just tell it the name or ID of the suite, and the MCP handles triggering all related tests together. **Can BugBug MCP help with firewall setup?** Yes, use the `get_ips` tool. It pulls all the necessary IP addresses you need to pass along to your network or security team for allowlisting. **How do I check if a test run passed successfully?** Use the `get_test_run` tool. This allows you to query the specific status of one test, giving you details on whether it failed or passed and why. **How do I use the `list_projects` tool to see all my BugBug projects?** It lists every project associated with your account. You can then select a specific project ID to narrow down which tests and suites you want to manage. **What information can I retrieve about a single test suite using `get_suite`?** The tool pulls detailed metadata for a given test suite. This includes the suite's creation date, its associated environment, and how many individual tests it contains. **How do I use `list_test_runs` to track long-term testing trends?** This tool provides a list of recent test run records. By examining the timestamps and statuses from multiple runs, you can programmatically spot patterns or performance degradation over time. **If I need specific details on an individual test, how do I use `get_test`?** You provide the unique Test ID to retrieve its full definition. This includes things like the test's title, description, and which larger suite it belongs to. **How do I find my BugBug API Token?** Log in to your account, navigate to the **Integrations** tab in the sidebar, and copy your unique API Token. **Can I run tests in a specific environment?** Yes! Both `run_test` and `run_suite` tools accept an optional `environmentId` parameter to target specific deployment stages. **How do I get the IP addresses for allowlisting?** Use the `get_ips` tool to retrieve the list of high-fidelity IP addresses used by BugBug's cloud infrastructure programmatically.