$ loading_
Run exploratory browser tests and create reproducible bug reports for coding agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Argus" MCP server from askskill: Run: claude mcp add 'io-github-chriswu727-argus' -- uvx argus-testing
Use Argus to run exploratory browser testing on the signup page, focusing on form submission, required-field validation, and error messages. If you find issues, produce a bug report with reproduction steps and evidence.
A bug report describing the issue, reproduction steps, and supporting test evidence.
Use Argus to exploratory-test the checkout flow from add-to-cart to payment confirmation, record abnormal behavior, and turn findings into reproducible bug reports.
Findings across the key flow and issue reports that developers can reliably reproduce.
Use Argus to inspect the main interactions of this web app and organize any issues into evidence-first reports so a coding agent can continue debugging.
Evidence-based test results and defect descriptions ready for the fixing workflow.
After frontend changes, developers can use it for exploratory browser testing to catch issues early. Its reproducible bug reports help with follow-up fixing and verification.
When reviewing key page flows, product managers can use it to capture abnormal behavior. Evidence-first reports make team discussion and reproduction clearer.
It is an MCP tool for coding agents that provides evidence-first exploratory browser testing and reproducible bug reporting.
Based on the description, it covers both exploratory browser testing and bug reporting, with an emphasis on evidence-backed issue discovery and reproduction.
The provided material does not specify installation steps, runtime requirements, or API keys. See the source repository.
Use an agentic QA framework to generate, triage, and repair Playwright tests.
Automate web QA with Chrome DevTools checks and CI-ready reports.
Run end-to-end browser testing and quality debugging directly from your IDE.
Lets agents control a real Chromium browser for web interactions.
Run plain-English browser tests for AI agents in real Chrome.
Retrieve bug context and evidence to help coding agents diagnose issues.