playwright-mcp
Click on "Install 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., "@playwright-mcpTest login on the-internet.herokuapp.com with tomsmith and SuperSecretPassword!"
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.
playwright-mcp
An MCP server that gives Claude direct control of a real browser via Playwright — enabling AI-driven web testing, autonomous test execution, and live failure analysis through natural language.
What It Does
Connect this server to Claude Desktop or Cursor and Claude gains the ability to:
Navigate to any URL and read the full page state
Click elements, fill forms, and submit data
Take screenshots and attach them to its reasoning
Run arbitrary JavaScript in the page context
Assert expected conditions — pass/fail with full context
Analyze failures autonomously without you touching a test script
Example prompt to Claude:
"Test the login flow on the-internet.herokuapp.com. Use username 'tomsmith' and password 'SuperSecretPassword!'. Verify the success message and take a screenshot."
Claude will navigate, fill the form, click submit, assert the result, and take a screenshot — all without you writing a single line of test code.
Related MCP server: MCP Playwright Server
Architecture
┌──────────────────────────────────────────────────────┐
│ Claude Desktop / Cursor │
│ │
│ "Test the login flow on example.com" │
└──────────────────────┬───────────────────────────────┘
│ MCP (stdio)
┌──────────────────────▼───────────────────────────────┐
│ playwright-mcp server │
│ │
│ Tools: │
│ navigate → page.goto(url) │
│ get_page_state → title + text + elements + errors │
│ screenshot → page.screenshot() → base64 │
│ click → locator.click() │
│ fill → locator.fill(value) │
│ evaluate → page.evaluate(js) │
│ assert → built-in assertions (8 types) │
│ close_browser → browser.close() │
└──────────────────────┬───────────────────────────────┘
│ Playwright CDP
┌──────────────────────▼───────────────────────────────┐
│ Chromium (headless) │
└──────────────────────────────────────────────────────┘Tools
Tool | Description |
| Go to a URL, returns title + status code |
| Read title, URL, visible text, interactive elements, console errors |
| Capture full page or specific element as base64 PNG |
| Click by CSS selector or visible text |
| Type into input fields |
| Run JavaScript in the page context |
| Verify title, URL, text, element presence/absence, input values |
| Close browser and release resources |
Setup
Prerequisites
Node.js 18+
Claude Desktop or any MCP-compatible host
Install
git clone https://github.com/ademdeniz/playwright-mcp.git
cd playwright-mcp
npm install
npm run install-browsers # downloads Chromium
npm run buildConnect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"playwright": {
"command": "node",
"args": ["/absolute/path/to/playwright-mcp/dist/server.js"]
}
}
}Restart Claude Desktop. You'll see a 🔌 icon showing the server is connected.
Connect to Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"playwright": {
"command": "node",
"args": ["/absolute/path/to/playwright-mcp/dist/server.js"]
}
}
}QA Agent Setup (LibreChat + SSE)
Beyond stdio hosts, this server ships an SSE transport so Docker-hosted MCP clients — like a self-hosted LibreChat — can drive the browser over HTTP. This powers a full AI QA Engineer agent: a chat UI where you type test steps in plain English and watch them execute against a real browser, with tunable model parameters, reusable skills, and a local audit log of every tool call.
Run the SSE server
npm run start:sse # http://0.0.0.0:8931 — GET /sse, POST /messages, GET /health
PORT=9000 npm run start:sseBinds 0.0.0.0 so containers reach it via host.docker.internal.
Register in LibreChat (librechat.yaml)
mcpSettings:
allowedAddresses: # SSRF exemption for the host-mapped address
- 'host.docker.internal:8931'
mcpServers:
playwright:
type: sse
url: http://host.docker.internal:8931/sse
timeout: 300000Then build an agent in LibreChat's Agent Builder: attach the playwright MCP
tools, paste examples/librechat-agent-instructions.md
into the Instructions field, and add the skills from
examples/skills/ (app selector map, spec-writing
conventions, executable regression scenarios).
Model notes (learned the hard way)
Context window matters: Ollama defaults to 4096 tokens, which silently truncates tool schemas — the model then hallucinates Selenium code instead of calling tools. Run
OLLAMA_CONTEXT_LENGTH=8192 ollama serveminimum.Thinking models stall: qwen3-style reasoning burns minutes of monologue per tool call on modest hardware. Use a non-thinking instruct variant, or a fast cloud endpoint (Groq / Gemini free tiers) for the agent brain while the browser and tests stay local.
Some models batch tool calls: llama-3.3 emits all steps at once, which arrive in scrambled order. The server rejects concurrent calls with an instructive error so such clients recover by re-issuing steps one at a time.
Hardening built into the server
One tool at a time — concurrent calls are rejected, not queued, so a stray
close_browsercan never execute mid-scenarioLaunch lock — concurrent
getPage()calls share one Chromium launch instead of racing severalToken-lean page state —
get_page_statecaps text and element output, since agent loops re-pay for every past tool result on each roundCall logging — every tool call is logged with its arguments; when the client's transcript and reality disagree, the server log is ground truth
Example Flows
Login test
You: "Test login on https://the-internet.herokuapp.com/login
with tomsmith / SuperSecretPassword!"
Claude: navigate → fill username → fill password → click Login
assert text_visible "You logged into a secure area!" → ✓ PASSED
screenshot → saved to screenshots/login_success.pngBroken image analysis
You: "Check https://the-internet.herokuapp.com/broken_images
and tell me which images failed to load"
Claude: navigate → get_page_state → evaluate (check naturalWidth)
"2 of 3 images are broken — both return 404.
Root cause: server paths do not exist."Form validation
You: "Submit the contact form on example.com with empty fields
and verify the validation errors appear"
Claude: navigate → click Submit → get_page_state
assert element_exists ".error-message" → ✓
assert text_visible "This field is required" → ✓Project Structure
playwright-mcp/
├── src/
│ ├── server.ts # MCP server — tools, one-at-a-time execution, call log
│ ├── sse.ts # SSE transport — HTTP endpoint for Docker-hosted clients
│ ├── browser.ts # BrowserManager — single browser/page, launch lock
│ └── tools/
│ ├── navigate.ts # page.goto()
│ ├── getPageState.ts # title + text + elements + errors (token-lean)
│ ├── screenshot.ts # page/element screenshot → base64
│ ├── click.ts # locator.click() — selector preferred over text
│ ├── fill.ts # locator.fill()
│ ├── evaluate.ts # page.evaluate(js)
│ ├── assert.ts # 8 assertion types
│ └── closeBrowser.ts # browser.close()
├── examples/
│ ├── claude_desktop_config.json
│ ├── librechat-agent-instructions.md # QA agent system prompt for LibreChat
│ ├── skills/ # LibreChat skills — app map, spec conventions, scenarios
│ ├── login_flow.md
│ └── failure_analysis.md
├── package.json
└── tsconfig.jsonRelated Projects
This server is part of a broader AI-powered QA tooling portfolio:
appium-ai-agent — same MCP pattern for iOS/Android mobile test automation
flaky-guard — detect and score flaky tests from JUnit XML
self-healing-locator — automatic locator fallback chains for Selenium
What's Next
Trace recording — capture Playwright traces for failed sessions
Network interception — mock API responses mid-test
Multi-tab support
wait_fortool — wait for element, URL, or network idle
Author
Adem Garic — SDET / QA Engineer 6+ years in mobile and web test automation (Appium, Selenium, Playwright, Jenkins, BrowserStack) LinkedIn · GitHub
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-quality-maintenanceA Playwright-based MCP server that exposes a live browser as a traceable, inspectable, debuggable and controllable execution environment for AI agents.Last updated5,36857
- Alicense-qualityDmaintenanceAn MCP server that enables AI-powered browser automation, web scraping, and testing using Playwright across Chromium, Firefox, and WebKit. It allows users to perform actions like navigation, clicking, typing, and taking screenshots through natural language interfaces.Last updated14MIT
- Flicense-qualityCmaintenanceAn MCP server that enables AI assistants to perform web automation tasks such as navigation, clicking, and taking screenshots by running Playwright on Cloudflare Workers. It allows models to interact with the web through a set of browser control tools across platforms like Claude Desktop and GitHub Copilot.Last updated
- AlicenseCqualityDmaintenanceAn MCP server that gives Claude Code real browser control for web automation, testing, and screenshots.Last updated3296154MIT
Related MCP Connectors
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Live browser debugging for AI assistants — DOM, console, network via MCP.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ademdeniz/playwright-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server