# MCP Browser Verify

> Use browser automation MCP (Playwright/Browser/Browser-Use) to validate UI flows, capture screenshots, and reproduce issues. Use when visual verification or web flow testing is needed.

- Skill: `janjaszczak/mcp-browser-verify` (Agent Skill)
- Install (CLI): `npx skillmds@latest add janjaszczak/mcp-browser-verify`
- Raw SKILL.md: https://api.skillmd.com/api/skills/janjaszczak/mcp-browser-verify/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: janjaszczak (https://skillmd.com/u/janjaszczak)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/janjaszczak/mcp-browser-verify

---


# mcp-browser-verify

## Activation
- UI bug, layout mismatch, flow verification, auth journey, “sprawdź w przeglądarce”.
- Prefer `mcp-browserclaw` when BrowserClaw is connected (logged-in agent browser + cockpit).
- Do **not** use when the user needs CAPTCHA/2FA intervention or anti-bot in the **BrowserOS** human session — use `mcp-browseros` instead.

## Procedure
1. Define scenario: URL, credentials (if any), steps, expected result.
2. Run scripted navigation.
3. Capture evidence: screenshots + console/network errors.
4. Report deltas + actionable fix hints.

## Output
- Scenario + evidence + pass/fail + next fix step.