Browser-backed QA MCP for coding agents, with evidence and fix-ready reports.
git clone https://github.com/bhuman-ai/QAbro{
"mcpServers": {
"qabro": {
"command": "node",
"args": ["/path/to/QAbro/dist/index.js"]
}
}
}MCP Servers overview
# Before Users Do Browser-backed QA for coding agents. Before Users Do is a hosted MCP server that lets Codex, Cursor, and other compatible coding agents test a reachable web app, collect browser evidence, and return a fix-ready report before the feature ships. [Install the QA MCP](https://beforeusersdo.com/qa-mcp) · [Read the setup guide](https://beforeusersdo.com/docs) · [View the official MCP Registry record](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.bhuman-ai%2Fbeforeusersdo) ## What the agent gets - Browser-backed flow testing against a reachable preview - Screenshots and recordings tied to the affected step - Console errors, page errors, and failed network requests - An explicit `pass`, `needs_fix`, `needs_review`, or `timed_out` outcome - A focused report the coding agent can use for the next change ## Hosted MCP endpoint ```text https://mcp.beforeusersdo.com/mcp ``` Create an MCP key through the [public setup guide](https://beforeusersdo.com/docs#start), then add the hosted connection to your MCP-capable coding agent. ## Why QA MCP instead of browser control alone? A browser tool can click and type. Before Users Do adds the QA contract around those actions: a test goal, an evidence trail, a trustworthy outcome, and a handoff back to the code. Durable Playwright or end-to-end test suites are still valuable for known regressions. Before Users Do is designed to help the agent inspect the newly finished flow and catch problems that have not become tests yet.
What people ask about QAbro
What is bhuman-ai/QAbro?
+
bhuman-ai/QAbro is mcp servers for the Claude AI ecosystem. Browser-backed QA MCP for coding agents, with evidence and fix-ready reports. It has 0 GitHub stars and was last updated today.
How do I install QAbro?
+
You can install QAbro by cloning the repository (https://github.com/bhuman-ai/QAbro) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is bhuman-ai/QAbro safe to use?
+
bhuman-ai/QAbro has not been audited yet by our security agent. Review the original repository on GitHub before using it in production.
Who maintains bhuman-ai/QAbro?
+
bhuman-ai/QAbro is maintained by bhuman-ai. The last recorded GitHub activity is from today, with 13 open issues.
Are there alternatives to QAbro?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy QAbro to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/bhuman-ai-qabro)<a href="https://claudewave.com/repo/bhuman-ai-qabro"><img src="https://claudewave.com/api/badge/bhuman-ai-qabro" alt="Featured on ClaudeWave: bhuman-ai/QAbro" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!