MCP servers and agent tools for Playwright
AgentSidekick indexes 84 DER agent products that mention Playwright; 34 of them have a full profile and are listed below. The most-starred tools that are their own repository are Browser Use (122k stars), Playwright MCP (40k stars) and CloakBrowser (33k stars) SRC. Figures as of 2026-11-21.
Playwright tools with a full profile
Search the directoryRanked by GitHub stars of the product's own repository. Products that live in a subfolder of a larger repository (marked “repo”) show that whole repository's stars and are ranked after them; products without a public repository come last.
| # | Product | Type | Hosting | Licence | Stars | Last push | Publisher | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | Browser UsePython library that lets LLM agents control a Playwright/CDP browser by reading page state and issuing actions, with a hosted cloud option. | Library | Remote and local | MIT | 122k | today | browser-use | |
| 2 | Playwright MCPMCP server that exposes Playwright browser control to agents using accessibility-tree snapshots instead of screenshots. | Developer tool | Local | Apache-2.0 | 40k | 3d ago | microsoft | |
| 3 | CloakBrowserStealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed. | Agent project | — | MIT | 33k | 1d ago | CloakHQ | |
| 4 | StagehandBrowser automation SDK that mixes Playwright-style code with natural-language act, extract and observe primitives and an agent mode. | SDK | — | MIT | 26k | today | browserbase | |
| 5 | nopecha-extensionAutomated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more. | Agent project | — | MIT | 11k | 1mo ago | NopeCHALLC | |
| 6 | playwright-skillGeneral-purpose Playwright automation for coding agents | Agent skill | — | MIT | 3.3k | 20d ago | lackeyjb | |
| 7 | claude-motion-designA Claude Code skill to make motion design videos in pure code: HTML + Playwright + ffmpeg. No After Effects, no Remotion license. | Agent skill | — | MIT | 875 | 1mo ago | howseen.ai | |
| 8 | playwright_mcpinvisible playwright mcp: Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use. | MCP server | — | MIT | 868 | 1d ago | oss-invisible | |
| 9 | invisible_playwright_mcpAI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions. | MCP server | Local | MIT | 868 | 1d ago | feder-cr | |
| 10 | google-searchA Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration. | MCP server | — | — | 629 | 1y ago | web-agent-master | |
| 11 | playwright-skillTestDino Playwright Skill: AI-powered guides for Playwright best practices, made by testdino.com. | Agent skill | — | MIT | 421 | 5d ago | testdino-hq | |
| 12 | claude-show-your-workClaude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows. | Plugin | — | MIT | 313 | 16d ago | iamumeransari | |
| 13 | CloakBrowser MCPPlaywright MCP-compatible browser automation bridge for CloakBrowser Chromium. | MCP server | Local | MIT | 181 | 1d ago | swimmwatch | |
| 14 | coder_evalPlaywright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates. | Agent skill | — | Apache-2.0 | 160 | 1d ago | UiPath | |
| 15 | mcp-accessibility-scannerMCP server for automated web accessibility scanning with Playwright and Axe-core. | MCP server | Local | MIT | 59 | today | JustasMonkev | |
| 16 | PageMapStructured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy | MCP server | Local | — | 36 | 6mo ago | Retio-ai | |
| 17 | cdpilotZero-npm-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium. | MCP server | Local | MIT | 34 | 5d ago | mehmetnadir | |
| 18 | PlayGuardProxy MCP for Playwright, Figma, DevTools, Shopify Dev, Context7 — fewer tokens, caching | MCP server | Local | MIT | 24 | 11d ago | ZenyaDAR | |
| 19 | OneTool MCPOne MCP for devs incl Brave,Google,Tavily,Context7,AWS,Excalidraw,DB,GitHub,DevTools,Playwright | MCP server | — | GPL-3.0 | 24 | 1d ago | beycom | |
| 20 | NetwrightPlaywright-style automation of .NET desktop apps (WPF, WinForms, WinUI) for AI agents. | MCP server | Local | MIT | 23 | 20d ago | ricfanin | |
| 21 | Terminal MCP ServerMCP server for AI agents to interact with terminal applications. Think Playwright for terminals. | MCP server | Local | MIT | 21 | 10mo ago | aybelatchane | |
| 22 | Playwright Cloud BrowsersManaged Playwright cloud browsers for scalable browser automation and AI agent workflows | MCP server | Remote | MIT | 18 | 25d ago | microsoft.com | |
| 23 | mantisThe web as short, numbered text for AI agents: a lean browser interface over Playwright. | MCP server | Local | MIT | 18 | 13d ago | perzianhq | |
| 24 | Vibe Test — Browser Testing AgentCode-aware browser testing agent — 14 Playwright tools for AI code editors via MCP | MCP server | Local | MIT | 18 | 7d ago | AishwaryShrivastav | |
| 25 | BrowsegrabToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab. | MCP server | Local | MIT | 0 | 7mo ago | ArkNill | |
| 26 | webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. | Agent skill | Local | — | — | 5d ago | anthropics | |
| 27 | cherry-regression-testRun Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners. | Agent skill | Local | AGPL-3.0 | — | today | CherryHQ | |
| 28 | playwrightBrowser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows. | Plugin | Local | Apache-2.0 | — | today | anthropics | |
| 29 | playwright-interactivePersistent browser and Electron interaction through `js_repl` for fast iterative UI debugging. | Agent skill | Local | — | — | 24d ago | openai | |
| 30 | playwrightUse when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script. | Agent skill | Local | — | — | 24d ago | openai | |
| 31 | playwright-skillWrite and run scoped Playwright browser automation, responsive checks, screenshots and login-flow tests with a local Node executor. | Agent skill | Local | MIT | — | 1d ago | sickn33 | |
| 32 | webapp-testingTo test local web applications, write native Python Playwright scripts. | Agent skill | Local | MIT | — | 1d ago | sickn33 | |
| 33 | e2e-testing-patternsMaster end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards. | Agent skill | Local | MIT | — | 3d ago | wshobson | |
| 34 | tiktok-upload使用仓库现有 Patchright/Playwright Chrome 上传器登录并发布 TikTok 视频。Use when 用户要发布 TikTok 视频,且当前环境可访问本仓库及其本地 Chrome 配置。 | Agent skill | Local | MIT-0 | — | 1mo ago | dreammis |
Hosting across all 34 profiled: 1 remote, 21 local, 1 both, 11 not declared. DER
Product-type mix
Which forms the tools take. Indexed covers every matching record; profiled only those with a page.
| Type | Indexed | Share | Profiled |
|---|---|---|---|
| MCP servers | 63 | 75.0% | 15 |
| Agent skills | 12 | 14.3% | 12 |
| Plugins | 4 | 4.8% | 2 |
| Agent projects | 2 | 2.4% | 2 |
| Agent SDKs | 1 | 1.2% | 1 |
| Libraries | 1 | 1.2% | 1 |
| Developer tools | 1 | 1.2% | 1 |
What these tools do
Most common capabilities among the profiled tools, matched from their descriptions by keyword rules.
Capabilities of Playwright toolsDER
Profiled products mentioning Playwright, by capability, top 10. A product can have several. As of 2026-11-21.
Show the data as a table
| profiled products | |
|---|---|
| Browser Control | 34 |
| Headless Browsing | 34 |
| Web Scraping | 10 |
| E2E Testing | 6 |
| Browser Agents | 5 |
| Computer Use | 4 |
| Proxies & Anti-bot | 4 |
| Debugging | 4 |
| Test Automation | 3 |
| Cloudflare Platform | 2 |
Demand signal
How often developers discuss this integration alongside MCP in public GitHub issues.
21,121 SRC public GitHub issues contain the phrase Playwright mcp
(search run 2026-11-21). Run the same search on GitHub.
This measures developer discussion, not buyers or revenue: an issue may be a bug report, a feature request or a passing mention. The count is GitHub's own estimate for the query "Playwright mcp" in:title,body is:issue.
Segment statisticsDER
All 84 indexed products, not only profiled ones. Calculated 2026-11-21.
- Launches
- 31 in the last 90 days, 12 in the 90 days before (+158%)DER
- Products with a repository
- 55 of 84 have whole-repository star countsDER
- Combined stars
- 239,813DER
- Median stars
- 5DER
- Largest project's share
- 51% of all stars in the segmentDER
- Concentration (HHI)
- 0.318, as concentrated as about 3 equally starred projectsDER
- Open-source share
- 75%DER
- Label
- Lagging the catalogueDER
How the label is set: size is this integration's percentile among all 111 integrations by indexed products (80th or above is crowded, 30th or below is thin). Momentum compares the ratio of launches in the last 90 days to the 90 before with the same ratio for the whole catalogue, so a booming ecosystem does not make every segment look like it is accelerating; it needs at least 5 launches across both windows. A segment can launch more products than last quarter and still be labelled slowing if the catalogue grew faster.
Vendor API
Playwright has a public API CUR. API docs (as recorded) The link has not been checked since it was recorded.
Playwright is not recorded as primarily a paid business product.
Opportunity score
Better agent tooling for Playwright scores 57.3 HEU of 100 (demand component 98, gap 21; competition high, confidence medium; calculated 2026-11-21). Scores rank integrations against each other; they do not predict revenue.
How products are matched, and the limits
A product is counted when its name, description or repository topics contain one of these aliases (case-insensitive, whole words): playwright
, playwright mcp
, playwright test
. A product named exactly “Playwright” is skipped, since it is the service itself.
Which alias matched, across the 84 indexed records: playwright
84.
Keyword matching over-counts tools that only mention Playwright in passing (for example as where their code is hosted) and misses tools that integrate with it without naming it. Treat the counts as an upper bound on dedicated tools and a lower bound on everything that touches Playwright.
No profiled product's publisher, GitHub owner or repository owner matches Playwright's own name, so this page does not split vendor tools from community ones.
Sources
- GitHub issue search: github.com (external)checked
- API documentation (as recorded, unverified): playwright.dev (external)check date not recorded
Product records come from the official MCP Registry, GitHub, Open VSX and plugin marketplaces; each profile lists its own sources. Methodology
Page data last updated .