BugBug MCP. Automate Web Testing from Your Chat Window
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
BugBug MCP Server. Automate web application testing and quality assurance using natural language commands. Your AI client runs high-fidelity, automated browser tests, catches regressions, and provides detailed reports without you touching a dashboard.
Trigger test suites, list projects, and monitor historical performance programmatically.
What your AI agents can do
Get ips
Retrieves the BugBug IP addresses required for firewall allowlisting.
Get suite
Gets specific details about a single test suite.
Get suite run
Checks the current status and results for a specific test suite run.
Retrieves a list of every project configured in your BugBug account.
Retrieves a list of all defined test suites within your projects.
Retrieves a list of all granular, reusable test cases.
Initiates a full, high-fidelity test run for a selected test suite.
Executes an isolated run for one specific test case.
Checks the current status and detailed results of a specific test suite execution.
Checks the current status and detailed results of a specific individual test run.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
BugBug MCP Server: 12 Tools for QA and Testing
Manage, run, and inspect every aspect of your web application's quality assurance pipeline using these 12 specialized tools.
019dd0c6get ips
Retrieves the BugBug IP addresses required for firewall allowlisting.
019dd0c6get suite
Gets specific details about a single test suite.
019dd0c6get suite run
Checks the current status and results for a specific test suite run.
019dd0c6get test
Retrieves detailed information for a single test case.
019dd0c6get test run
Checks the current status and results for a specific test case run.
019dd0c6list projects
Lists every project currently set up in BugBug.
019dd0c6list suite runs
Lists the most recent completed test suite executions.
019dd0c6list suites
Lists all defined test suites for your projects.
019dd0c6list test runs
Lists the most recent completed individual test executions.
019dd0c6list tests
Lists all defined, reusable test cases.
019dd0c6run suite
Starts a full automated test run for a selected test suite.
019dd0c6run test
Starts an isolated automated test run for a single test case.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with BugBug, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
This BugBug MCP Server lets your AI client automate web testing and quality assurance using natural language. Your agent runs high-fidelity, automated browser tests, catching regressions and giving you detailed reports without you ever having to touch a dashboard. You'll use it to trigger test suites, list projects, and monitor historical performance programmatically.
list_projects lets you see every project set up in BugBug. list_suites lists all the defined test suites for your projects. list_tests lists every granular, reusable test case you've defined.
run_suite kicks off a full automated test run for a selected test suite. run_test executes an isolated, automated run for a single test case. get_suite_run checks the current status and detailed results for a specific test suite run. get_test_run checks the current status and detailed results for a specific individual test run. list_suite_runs lists the most recent completed test suite executions, and list_test_runs lists the most recent completed individual test executions. get_ips retrieves the BugBug IP addresses you need for firewall allowlisting.
How BugBug MCP Works
- 1 Subscribe to the BugBug server and get your API Token from the BugBug dashboard.
- 2 Provide your agent with the necessary context (e.g., 'list all suites for the checkout flow').
- 3 Your agent calls the appropriate tool (e.g.,
list_suites) and you get the data back to continue the conversation.
The bottom line is you connect your AI client to BugBug and let it run your testing commands through natural conversation, eliminating manual dashboard interactions.
Who Is BugBug MCP For?
This is for the QA Engineer who needs to trigger regression tests across environments without leaving their terminal. It's for the Developer who needs to verify application quality right after a push without switching tools. And for the DevOps team member who needs to automate IP fetching for firewalls.
Runs full regression suites and checks historical run data using natural language prompts.
Verifies application quality after a deployment by running specific tests, all without leaving their IDE or chat workspace.
Automates fetching BugBug's IP addresses for firewall allowlisting and monitors suite performance via simple AI queries.
What Changes When You Connect
- Triggering full test suites is simple. Instead of navigating to a dashboard, you just tell your agent to
run_suitefor the 'Smoke Test' suite. It handles the execution and gives you a run ID. - You don't have to dig through run logs. To check results, just ask your agent to
get_suite_runorget_test_run. It pulls the status and high-fidelity report instantly. - Need to know if the environment is secure? Use
get_ipsto pull all necessary BugBug IP addresses. You can feed these directly into your firewall rules. - Track quality trends easily. Use
list_suite_runsto see a history of the last twenty runs. This lets you track if a specific feature started failing over time. - Need to debug a specific failure? Use
list_teststo find the test ID, then run it individually withrun_test. This isolates the failure point immediately. - Keep everything organized. Use
list_projectsandlist_suitesto scope your requests. This ensures your agent runs tests only on the intended project or suite.
Real-World Use Cases
Detecting a post-deployment regression
A developer just pushed a new checkout service. They ask their agent: 'Run the main checkout suite for the Staging environment.' The agent calls run_suite, monitors the result, and reports back if the payment validation steps failed. The problem is solved without leaving their IDE.
Onboarding a new firewall rule
The DevOps team member needs to update the corporate firewall. They ask their agent to run get_ips. The agent returns a list of IP ranges, which the team uses to update the network security group. This is a simple, direct data retrieval task.
Investigating intermittent failures
A QA Engineer notices a test fails randomly. They use list_tests to find the failing test ID, then use run_test to isolate that single test case. They repeat this across different environments until they pinpoint the exact failure point.
Auditing historical performance
A product manager wants to see how the 'login flow' has performed over the last month. They ask their agent to use list_suite_runs and analyze the aggregated pass/fail rates, getting a quick trend report without manual database querying.
The Tradeoffs
Sequential, manual API calls
Manually calling list_suites, then copy-pasting the ID into a dashboard, then manually triggering run_suite in a separate tab. This takes five minutes and requires context switching.
→
Just tell your agent: 'Run the Smoke Test suite for the production environment.' The agent handles the list_suites lookup and the run_suite call in one go.
Ignoring project scope
Running a test suite (run_suite) without first confirming the project using list_projects. This can cause the test to run against the wrong environment or an outdated codebase.
→
Always start by asking your agent to list_projects and confirm the target project. Then, use list_suites to find the correct suite before executing the run.
Treating data as a black box
Getting a list of test runs (list_test_runs) and not following up to check the status. You get the IDs, but no actual pass/fail status or failure steps.
→
After getting the run IDs, immediately follow up with get_test_run and specify the ID. This pulls the real, actionable status and the high-fidelity report.
When It Fits, When It Doesn't
Use this if your primary job is to run, check, and track automated browser tests. You need to trigger full test cycles (run_suite) or deep-dive into single test cases (run_test) and need to pull historical data (list_suite_runs).
Don't use this if you need to manage the underlying code or write the tests themselves. For that, you need a code repository integration. Don't use this if your main task is simply tracking environment variable changes; use a dedicated secrets manager tool instead. If you only need the IP list, get_ips handles that single task fine, but for full QA, this server is what you need.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by BugBug. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Debugging a failing web page shouldn't require five different tabs and three different tools.
Today, finding out why a checkout button fails means navigating to the QA dashboard. You check the 'Test Runs' tab, find the run ID, copy it, paste it into the 'History' tab, and then search for the specific test case. This sequence is slow, prone to copy/paste errors, and requires you to keep track of three different identifiers.
With the BugBug MCP Server, you just tell your agent: 'Show me the results for the checkout button test.' The agent handles listing the test, running the check, and pulling the full report in one conversation. You get the answer without the clicks.
BugBug MCP Server: Run tests and manage quality from your agent.
You eliminate the need to manually check the test status. Instead of finding the run ID via `list_test_runs` and then manually calling `get_test_run` in another window, your agent does both steps and presents the final status immediately. It's a single, natural command.
The process is now declarative. You state the goal—'Verify the login flow'—and the agent figures out the exact sequence of tools (`list_tests`, `run_test`, `get_test_run`) to get you the outcome. That's the difference.
Common Questions About BugBug MCP
How do I run a full regression suite using BugBug MCP Server? +
You tell your agent to run_suite and specify the suite name or ID. The agent handles the execution and provides the run ID. You can then use get_suite_run to track its progress until it finishes.
Can I list all my projects using BugBug MCP Server? +
Yes, use the list_projects tool. This returns a list of every project configured in your BugBug account, giving you scope context for your tests.
What is the difference between `list_test_runs` and `list_suite_runs` in BugBug MCP Server? +
Use list_suite_runs when you want to see the history of entire test collections. Use list_test_runs when you only want to see the history of a single, isolated test case execution.
How do I get the IP addresses using BugBug MCP Server? +
Use the get_ips tool. This retrieves the necessary BugBug IP addresses, which you can then use to update your organization's firewall rules.
How do I use `list_suites` to manage my test environments in BugBug MCP Server? +
The list_suites tool returns a list of all defined test suites. You can use this to identify which specific testing groups you need to run or inspect. This helps you organize your quality assurance efforts by name or ID before triggering a test run.
What is the purpose of the `get_suite` tool in BugBug MCP Server? +
The get_suite tool fetches detailed metadata for a single, specified test suite. This lets you see the composition of the suite, such as which individual tests it contains and its configuration settings. You need this info before running or modifying the suite.
How do I programmatically check the status of a test using `get_test_run` in BugBug MCP Server? +
The get_test_run tool provides the current status and results for a specific, single test run. This lets your agent quickly verify if one test passed or failed. You use this when you only care about the outcome of one particular piece of functionality.
What happens when I run a test using the `run_test` tool in BugBug MCP Server? +
The run_test tool immediately initiates an execution for a specific test. Your agent receives a run ID, which you then use with other tools to monitor the progress. This is the most direct way to check a single feature's quality after a small code change.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Phone Validator Engine
Stop LLMs from hallucinating phone numbers. Validates and formats numbers to E.164 natively.
Nalpeiron V10
Protect your software with license management, usage tracking, and entitlement enforcement for desktop and cloud applications.
HTML DOM Query Engine
Extract specific text and attributes from massive HTML payloads instantly using CSS selectors. Fast, memory-efficient DOM parsing.
You might also like
DevSkiller
Equip your AI agent to manage technical assessments, track candidates, and monitor test results via the DevSkiller API.
Teyuto
Build your own video streaming platform with monetization, audience analytics, and content management for video creators.
Route4Me
Connect your AI assistant to Route4Me to orchestrate complex fleet logistics, solve multi-stop route optimizations, and track real-time vehicle GPS directly via chat.