Bezlo MCP Server
Provides true-to-size Android device frames for web pages, enabling AI agents to capture screenshots, inspect interactive elements, run layout diagnostics, execute tap/type/scroll flows, and perform device matrix runs with report and video evidence.
Provides true-to-size iPhone and iPad frames for web pages, enabling AI agents to capture screenshots, inspect interactive elements, run layout diagnostics, execute tap/type/scroll flows, and perform device matrix runs with report and video evidence.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Bezlo MCP Serverscreenshot localhost:3000 on iPhone 16 and check for overflow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bezlo — open agent layer
Bezlo puts any web page inside a true-to-size iPhone / iPad / Android frame and lets an
AI agent see it and act on it: screenshots, interactive-element lists, layout
diagnostics (overflow, safe-area, touch identity), console/page errors, network mocks,
tap/type/scroll flows, device matrix runs — and report.json / JUnit / mp4 evidence.
This repository is the MIT-licensed agent layer:
mcp/— MCP stdio server + CLI + session/capture engine (also on npm asbezlo-mcp)action.yml+examples/— composite GitHub Action (PR screenshots + JUnit + video)skill/— thebezlo-previewskill for Claude Code / skills-compatible agentsserver.json— official MCP registry manifestdocs/MCP.md— full tool reference
The Chrome extension itself is proprietary and lives in a separate private repo
(extension/, store art, brand). This repository contains no extension code, store
assets or brand artwork. The name Bezlo and its logo are not licensed for reuse.
Install
# MCP (Claude Code / Claude Desktop / Cursor)
npm install -g bezlo-mcp
claude mcp add bezlo -- npx -y bezlo-mcp
# or run from a checkout
node mcp/cli.mjs --listThe package bundles no browser: install Chrome/Chromium (or set RP_CHROME). Chrome for
Testing is recommended; WebKit mode additionally needs npx playwright install webkit.
Related MCP server: weblab
Quick CLI
node mcp/cli.mjs --url http://localhost:3000 --device iphone16 --out shot.png
node mcp/cli.mjs --url http://localhost:3000 --matrix --devices iphone16,ipadpro11,px10 --out ./matrix
node mcp/cli.mjs --url http://localhost:3000 \
--actions '[{"type":"click","text":"Sign in"},{"type":"type","selector":"#email","value":"a@b.c","submit":true}]' \
--record --assert '[{"type":"noOverflow"},{"type":"noConsoleErrors"}]' --out after.pngGitHub Action
- uses: gba3124/bezlo@main
id: bezlo
with:
url: http://localhost:3000
device: iphone16
steps: '[{"type":"click","text":"Sign in"}]'
asserts: '[{"type":"noOverflow"},{"type":"noConsoleErrors"}]'
record: 'true'Artifacts: final screenshot, report.json, junit.xml, optional mp4/gif.
Outputs: pass, report, junit, video, gif, screenshot, artifacts.
Engines
chromium (default) — Chrome's own emulation engine (same as the extension's frames): real touch, mobile UA and client hints, DPR; full recording and CDP accessibility.
webkit — Playwright WebKit, a Safari-flavoured approximation (not real iOS Safari; no recording / CDP a11y).
License
MIT — see LICENSE. The Chrome extension, store assets and the Bezlo brand are not
covered by this license and are not part of this repository.
This server cannot be deployed
Maintenance
Related MCP Connectors
Let your AI agent control real iPhones: screenshots, tap, swipe, type and open apps.
1Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.
Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs.
Let your AI agent operate any website through a real, logged-in browser session.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to remotely control, debug, and automate real browsers, iOS simulators, and Android emulators, including navigation, element inspection, interaction, screenshots, and mobile gestures.47 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to drive real Chromium, WebKit, or Firefox browsers — opening named sessions, running ordered steps like clicks, typing, and assertions, and reading back text, console/network logs, and screenshots — so web apps can be tested and explored end to end. It starts and shares dev servers, attaches to already-running browsers, and can fake API responses or device settings.1 npmMIT

agentlaneofficial
AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to drive and inspect isolated app instances across web, iOS, and Android, with tools for reading screens, running interactions, and capturing screenshots or evidence.36 npm1MIT- AlicenseNot gradedqualityAmaintenanceEnables AI agents to drive live mobile and desktop web sessions while measuring the UI, returning contrast ratios, touch-target sizes, overflow, and theme-drift findings as precise text with selectors attached. Agents can also navigate, tap, type, scroll, switch device profiles and themes, capture the shared frame, and read notes pinned by the human watching the same session.109 npmMIT