Playwright MCP servers
MCP servers that connect an AI agent to Playwright: driving a real browser for navigation, scraping and end-to-end tests. We have classified 87 so far, listed below and ranked by their independent trust score.
87 catalogued · how we score
Playwright at a glance
- Highest score
- 93 io.github.hubertgajewski/playwright-report-mcp
- Median score
- 71
- Scored
- 87 of 87
- Rescanned in 7 days
- 85
npm 49 · remote 34 · pypi 7 · oci 4 · mcpb 1 · figures as of 2026-09-20 13:30 UTC · how we score
All 87 by trust score Trust score 0–100
- npm 93
io.github.hubertgajewski/playwright-report-mcp
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
- npm 92
io.github.microsoft/playwright-mcp
Playwright Tools for MCP
- npm 91
Local-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key.
- npm 91
Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local
- npm 89
MCP server that reverse-engineers a locked rebuild spec from an existing app.
- remote 89
DSGVO.pro — German Digital-Law Compliance
Search 26 German/EU statutes free — then scan any website against 33 compliance modules.
- npm 89
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
- npm 88
Debug PWAs in your real browser via MCP: service-worker, cache, installability & framework state.
- npm 88
Local QA MCP: scan URLs, inspect pages, generate Playwright repros, and run tests.
- npm 87
Extract a visual contract from a reference page and measure an implementation against it
- npm 86
io.github.oguzc/playwright-wizard-mcp
MCP server providing Playwright test generation wizard with intelligent prompts and best practices
- npm 85
io.github.prashantsinghmangat/tracebug
AI agents read TraceBug bug reports (console, network, replay, repro timeline) from local disk.
- npm 84
io.github.vola-trebla/flakiness-knowledge-graph-mcp
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
- npm 84
io.github.vola-trebla/playwright-spatial-layout-mcp
MCP server that gives AI agents geometric spatial awareness of web page layouts using Playwright
- npm 83
io.github.aditya-ariosity/wcag-accessibility
A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.
- npm 83
Turn your AI host into a product videographer: scripted app demos, voice-over, captions, MP4/GIF.
- remote · pypi 83
Score any URL against a real design contract — 42 checks, A-F grade, token + motion validation.
- npm 82
io.github.anthonybono21-cloud/leapfrog
Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.
- npm · oci 82
io.github.dinesh-nalla-se/playwright-mcp
Playwright Tools for MCP
- npm 82
Gridproof your UI — automated spacing & grid QA in the agent loop (MCP server).
- npm 82
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
- npm 81
io.github.vola-trebla/playwright-network-chaos-mcp
MCP server that gives AI agents dynamic network chaos control over Playwright browser sessions
- npm 80
io.github.aethynio/aethyn-browser-mcp
Local Playwright browser through residential proxies — agent picks country + sticky identity
- npm 80
Play with your app's design in the browser: load a build, turn the knobs, export the code.
- npm 80
io.github.inSideos-designs/cowork-qa
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
- npm 80
Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.
- npm 80
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
- npm 80
io.github.XXO47OXX/spa-reader-mcp
MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content
- npm 79
io.github.vola-trebla/zod-contract-mock-forge-mcp
MCP server for deterministic mock generation and API contract scaffolding using Zod schemas
- npm 78
com.pulsemcp/playwright-stealth
Browser automation using Playwright with optional stealth mode to bypass anti-bot protection.
- pypi 78
The accessibility layer for AI coding agents: audit, fix, document and watch - WCAG 2.2.
- remote · npm 78
io.github.meltingpixelsai/zero-core-tools
Web scraping, code review, content gen, sentiment. Zero Core Tools.
- npm 78
io.github.vola-trebla/playwright-trace-decoder-mcp
MCP server for unpacking and analyzing Playwright trace.zip archives
- npm 78
Browser MCP: drive a real Chromium via Playwright with compact ref-addressable page snapshots
- remote 77
com.thenextgennexus/enterprise-mcp-gateway
Unified gateway exposing 150+ tools across all NexGenData MCP servers via one endpoint.
- npm 77
Convert HTML or URLs to PDF documents powered by Playwright
- npm 76
An MCP server that provides browser automation
- npm 76
UISandbox deprecated
Test your design on the real thing: load a built web app, turn its knobs, verify 1:1, export.
- remote · npm 76
Continuous website testing by Validoria — monitor security, SEO, performance, and accessibility.
- remote 74
Readiness scorer — can an agent sign up to your SaaS?
Probe a signup URL you own and score whether an AI agent can sign up unaided.
- npm 73
Detect unnatural Korean and English mid-word wrapping in responsive web pages.
- npm 72
Catch bad animations before they ship. Deterministic motion audit + vision-LLM design review.
- npm 72
Persistent 3D/2D spatial world model for AI agents with entity tracking and simulation.
- npm 71
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
- pypi 70
MCP server for AI agents: discover a web page's data sources and drive the page to reach them.
- npm 68
io.github.CapMonsterCloud/capmonster-mcp-patchright-captcha-solver
Browser automation MCP for solving captchas with CapMonster Cloud via Patchright.
- remote 68
27 pay-per-call web tools for agents: scrape, screenshot, PDF, OCR, search, prices, validation. x402
- remote · npm 66
io.github.serkan-ozal/browser-devtools-mcp
Playwright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.
- pypi 63
io.github.paipaipai666/nexus-browser-mcp
Event-driven deterministic browser MCP: HITL gates, audit, console/network/perf observability.
- remote 59
ISO 639 language tag en.
- remote 59
Current local time in America/Los_Angeles.
- remote 58
ISO 639 language tag zh.
- remote 57
Fresh cache hint
- remote 57
Public ISO 3166-1 record for CN.
- remote 57
Public ISO 3166-1 record for MT.
- remote 57
Public ISO 3166-1 record for MV.
- remote 57
gitignore rule count, body discarded
gitignore rule count, body discarded
- remote 57
HTML tag count, markup discarded
HTML tag count, markup discarded
- remote 57
GET is allowed
- remote 57
Current local time in Asia/Ashgabat.
- remote 57
Current local time in Indian/Mauritius.
- remote 57
Current local time in Pacific/Efate.
- remote 57
Current local time in Pacific/Midway.
- remote 56
Nautical miles to kilometers, number discarded
Nautical miles to kilometers, number discarded
- remote 56
SHA-224 hex length, input discarded
SHA-224 hex length, input discarded
- remote 56
Return a three-step thinking template. Prompt discarded.
- remote 56
Tiger hex length, input discarded
Tiger hex length, input discarded
- remote 56
begin-line mode shape, input discarded
begin-line mode shape, input discarded
- remote 56
Week-of-year 1-53 band
- remote 56
XXH128 hex length, input discarded
XXH128 hex length, input discarded
- mcpb · oci 54
Turn any website or API into structured JSON with LLM-authored declarative scraping configs.
- remote 53
US fluid drams to milliliters, number discarded
US fluid drams to milliliters, number discarded
- remote 53
MSSQL IDENTITY integer band, value discarded
MSSQL IDENTITY integer band, value discarded
- npm 49
Vibe Test — Browser Testing Agent
Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP
- oci 49
Converts HTML to Markdown with auto-summary and section extraction. Supports Playwright.
- npm · oci 49
Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium.
- npm 39
io.github.ObscuritySRL/bun-uia
Playwright for the Windows desktop, from Bun — drive native GUIs via UI Automation + MCP.
- npm 38
io.github.263311487-ux/dsh-verify
Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts.
- npm 38
io.github.JustasMonkev/mcp-accessibility-scanner
MCP server for automated web accessibility scanning with Playwright and Axe-core.
- npm · pypi 37
Drive a real Playwright browser: annotated screenshot + structured page state after every action.
- pypi 37
io.github.mechreaper007x/clipacanvas
Render HTML, CSS, SVG, and Canvas animations to MP4 locally via Playwright/Chromium and FFmpeg.
- pypi 36
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
- remote 36
Discover Playwright workflows, start runs, and inspect results in Playrunner Cloud.
- npm 34
io.github.katatan-org/katatan-TEST
KATATAN E2E testing agent set — Playwright + KATATAN MCP integration
- npm 31
io.github.fasteningcode/claudetest
Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.
- remote 0
com.clauxel.playwrightselectorguard/playwrightselectorguard-mcp dead
Playwright selector risk checks with healing suggestions and receipts.
- remote 0
ShipCheck dead
Independent preview-URL QA for coding agents. Playwright heuristics, pass/fail pack.
Every server here has been scored. A server is listed here because its description and tool definitions say it is built for Playwright. That is what the server declares about itself, not an integration we have tested, so check the score breakdown before you trust one. This classification currently runs only over servers that publish a hosted endpoint, so a Playwright server distributed solely as an installable package will not appear here yet, however clearly it belongs. Treat the ranking as a partial field rather than the whole one.
Common questions
What is a Playwright MCP server?
A Playwright MCP server exposes driving a real browser for navigation, scraping and end-to-end tests to an AI assistant over the Model Context Protocol, so the assistant can work with Playwright directly instead of you moving data in and out by hand. These come from the public MCP registry, and being listed there is not a review of the code, so the publisher is worth checking as closely as the feature list.
How do I get started with a Playwright MCP server?
Start from the ranked list on this page, then open a server's own page and read its score breakdown before you install anything. Every server listed here is a hosted endpoint, so that breakdown covers Endpoint Security, Transport & Reachability, Schema Quality & AI Usability, Stability & Change Management, Tool Coverage, Tool Safety and Capabilities. A Playwright server acts on your Playwright data, so check what access it asks for before you connect it. The same page carries install snippets for the common MCP clients.