Playwright Model Context Protocol server for browser automation
The Playwright MCP Server provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, and execute JavaScript in a real browser environment. It supports device emulation, allowing testing on 143 real device profiles, while offering features for easy installation and configuration for various setups.
·
A Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, generate test code, web scrapes the page and execute JavaScript in a real browser environment.
Test your web applications on real device profiles with a simple command:
// Test on iPhone 13 with automatic user-agent, touch support, and device pixel ratio
await playwright_resize({ device: "iPhone 13" });
// Switch to iPad with landscape orientation
await playwright_resize({ device: "iPad Pro 11", orientation: "landscape" });
// Test desktop view
await playwright_resize({ device: "Desktop Chrome" });Natural Language Support for AI Assistants:
Supports 143 devices: iPhone, iPad, Pixel, Galaxy, and Desktop browsers with proper emulation of viewport, user-agent, touch events, and device pixel ratios.
📚 View Device Quick Reference | Prompt Guide
You can install the package using either npm, mcp-get, or Smithery:
Using npm:
npm install -g @executeautomation/playwright-mcp-serverUsing mcp-get:
npx @michaellatman/mcp-get@latest install @executeautomation/playwright-mcp-serverUsing Smithery
To install Playwright MCP for Claude Desktop automatically via Smithery:
npx @smithery/cli install @executeautomation/playwright-mcp-server --client claudeUsing Claude Code:
claude mcp add --transport stdio playwright npx @executeautomation/playwright-mcp-serverInstall the Playwright MCP server in VS Code using one of these buttons:
Alternatively, you can install the Playwright MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"playwright","command":"npx","args":["@executeautomation/playwright-mcp-server"]}'# For VS Code Insiders
code-insiders --add-mcp '{"name":"playwright","command":"npx","args":["@executeautomation/playwright-mcp-server"]}'After installation, the ExecuteAutomation Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.
The Playwright MCP Server automatically installs browser binaries when you first use it. When the server detects that a browser is missing, it will:
No manual setup required! Just start using the server, and it handles browser installation for you.
If you prefer to install browsers manually or encounter any issues with automatic installation:
# Install all browsers
npx playwright install
# Or install specific browsers
npx playwright install chromium
npx playwright install firefox
npx playwright install webkitBrowsers are installed to:
%USERPROFILE%\AppData\Local\ms-playwright~/Library/Caches/ms-playwright~/.cache/ms-playwrightThis is the recommended mode for Claude Desktop.
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@executeautomation/playwright-mcp-server"]
}
}
}Note: In stdio mode, logging is automatically directed to files only (not console) to maintain clean JSON-RPC communication. Logs are written to ~/playwright-mcp-server.log.
When running headed browser on systems without display or from worker processes of IDEs, you can run the MCP server as a standalone HTTP server:
Note for Claude Desktop Users: Claude Desktop currently requires stdio mode (command/args configuration). HTTP mode is recommended for VS Code, custom clients, and remote deployments. See CLAUDE_DESKTOP_CONFIG.md for details.
# Using npx
npx @executeautomation/playwright-mcp-server --port 8931
# Or after global installation
playwright-mcp-server --port 8931The server will start and display available endpoints:
==============================================
Playwright MCP Server (HTTP Mode)
==============================================
Port: 8931
ENDPOINTS:
- SSE Stream: GET http://localhost:8931/sse
- Messages: POST http://localhost:8931/messages?sessionId=<id>
- MCP (unified): GET http://localhost:8931/mcp
- MCP (unified): POST http://localhost:8931/mcp?sessionId=<id>
- Health Check: GET http://localhost:8931/health
==============================================⚠️ CRITICAL: The
"type": "http"field is REQUIRED for HTTP/SSE transport!
For VS Code GitHub Copilot:
{
"github.copilot.chat.mcp.servers": {
"playwright": {
"url": "http://localhost:8931/mcp",
"type": "http"
}
}
}For Custom MCP Clients:
{
"mcpServers": {
"playwright": {
"url": "http://localhost:8931/mcp",
"type": "http"
}
}
}Important: Without "type": "http", the connection will fail.
For Claude Desktop: Use stdio mode instead (see Standard Mode above)
/health endpointMonitoring: The server includes a monitoring system that starts on a dynamically allocated port (avoiding conflicts). Check the console output for the actual port.
Note: For Claude Desktop, continue using stdio mode (Standard Mode above) for now.
Symptom: 400 error with message "Bad Request: No transport found for sessionId"
Solution:
Check configuration includes "type": "http"
{
"url": "http://localhost:8931/mcp",
"type": "http" // ← This is REQUIRED!
}Verify server logs show connection:
# Should see these in order:
# 1. "Incoming request" - GET /mcp
# 2. "Transport registered" - with sessionId
# 3. "POST message received" - with same sessionIdRestart both server and client
ssh -L 8931:localhost:8931 user@remote-serverThis project uses Jest for testing. The tests are located in the src/__tests__ directory.
You can run the tests using one of the following commands:
# Run tests using the custom script (with coverage)
node run-tests.cjs
# Run tests using npm scripts
npm test # Run tests without coverage
npm run test:coverage # Run tests with coverage
npm run test:custom # Run tests with custom script (same as node run-tests.cjs)The test coverage report will be generated in the coverage directory.
The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.
OPENAI_API_KEY=your-key npx mcp-eval src/evals/evals.ts src/tools/codegen/index.tsWhen adding new tools, please be mindful of the tool name length. Some clients, like Cursor, have a 60-character limit for the combined server and tool name (server_name:tool_name).
Our server name is playwright-mcp. Please ensure your tool names are short enough to not exceed this limit.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add playwright -- npx -y @executeautomation/playwright-mcp-server{
"mcpServers": {
"playwright": {
"args": [
"-y",
"@executeautomation/playwright-mcp-server"
],
"command": "npx"
}
}
}code --add-mcp '{"name":"playwright","args":["-y","@executeautomation/playwright-mcp-server"],"command":"npx"}'[mcp_servers.playwright]
command = "npx"
args = ["-y", "@executeautomation/playwright-mcp-server"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/mcp-playwright to learn what the "mcp-playwright" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx @michaellatman/mcp-get@latest install @executeautomation/playwright-mcp-server
npx @smithery/cli install @executeautomation/playwright-mcp-server --client claude
npx playwright install
npx playwright install chromium
npx playwright install firefoxclaude mcp add --transport stdio playwright npx @executeautomation/playwright-mcp-server| Name | What it does |
|---|---|
start_codegen_session | Start a new code generation session to record Playwright actions |
end_codegen_session | End a code generation session and generate the test file |
get_codegen_session | Get information about a code generation session |
clear_codegen_session | Clear a code generation session without generating a test |
playwright_navigate | Navigate to a URL |
playwright_screenshot | Take a screenshot of the current page or a specific element |
playwright_click | Click an element on the page |
playwright_iframe_click | Click an element in an iframe on the page |
playwright_iframe_fill | Fill an element in an iframe on the page |
playwright_fill | fill out an input field |
playwright_select | Select an element on the page with Select tag |
playwright_hover | Hover an element on the page |
playwright_upload_file | Upload a file to an input[type='file'] element on the page |
playwright_evaluate | Execute JavaScript in the browser console |
playwright_console_logs | Retrieve console logs from the browser with filtering options |
playwright_resize | Resize the browser viewport using manual dimensions or device presets. Supports 143+ device presets including iPhone, iPad, Android devices, and desktop browsers with proper user-agent and touch emula |
playwright_close | Close the browser and release all resources |
playwright_get | Perform an HTTP GET request |
playwright_post | Perform an HTTP POST request |
playwright_put | Perform an HTTP PUT request |
playwright_patch | Perform an HTTP PATCH request |
playwright_delete | Perform an HTTP DELETE request |
playwright_expect_response | Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait for its completion. |
playwright_assert_response | Wait for and validate a previously initiated HTTP response wait operation. |
playwright_custom_user_agent | Set a custom User Agent for the browser |
playwright_get_visible_text | Get the visible text content of the current page |
playwright_get_visible_html | Get the HTML content of the current page. By default, all <script> tags are removed from the output unless removeScripts is explicitly set to false. |
playwright_go_back | Navigate back in browser history |
playwright_go_forward | Navigate forward in browser history |
playwright_drag | Drag an element to a target location |
playwright_press_key | Press a keyboard key |
playwright_save_as_pdf | Save the current page as a PDF file |
playwright_click_and_switch_tab | Click a link and switch to the newly opened tab |
| Name | What it does |
|---|---|
Browser console logs | No description provided. |
Read live from the server on September 23, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/mcp-playwright)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "mcp-playwright" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.