Playwright MCP Server

What is Playwright MCP Server about?

Playwright MCP Server supplies a Model Context Protocol (MCP) endpoint that lets large language models control a real Playwright‑driven browser. Through this server, LLMs can navigate sites, take screenshots, extract data, run custom JavaScript, and even synthesize test scripts on the fly.

How to use Playwright MCP Server?

1. Installation – Install globally via npm, mcp‑get, or Smithery. The most common command is:

   npm install -g @executeautomation/playwright-mcp-server
   

   or using the recommended npx shortcut:

   npx -y @executeautomation/playwright-mcp-server
   

2. Configuration – Add the server to the client’s MCP configuration (e.g., Claude Desktop):

   {
     "mcpServers": {
       "playwright": {
         "command": "npx",
         "args": ["-y", "@executeautomation/playwright-mcp-server"]
       }
     }
   }
   

3. Invocation – From the LLM client, call the server’s tools (e.g., navigate, click, screenshot, scrape, run_js). The server returns structured results that the model can consume.

Key Features

• Full Playwright browser control (Chromium, Firefox, WebKit).
• Screenshot capture and visual diff.
• Automated test‑code generation in multiple languages.
• Page scraping with DOM extraction.
• Arbitrary JavaScript execution inside the page context.
• Jest‑based test suite with coverage reporting.
• Simple VS Code integration via install buttons or CLI.
• Compatibility with multiple LLM clients (Claude Desktop, Cursor, VS Code Copilot, etc.).

Use Cases

• Automated UI testing – Generate and run Playwright tests directly from an LLM prompt.
• Data extraction – Prompt an LLM to scrape tables, lists, or structured data from dynamic sites.
• Rapid prototyping – Let the model experiment with page interactions and instantly see results.
• Documentation assistance – Capture screenshots or page states for inclusion in technical docs.
• Debugging assistance – Execute custom JavaScript to inspect page state and feed findings back to the model.

FAQ

Q: Do I need a Playwright license? A: No, Playwright is open‑source and bundled with the server.

Q: Which browsers are supported? A: All browsers Playwright supports – Chromium, Firefox, and WebKit.

Q: Can I run the server locally without internet? A: Yes, after installing the npm package the server runs entirely offline.

Q: How do I add custom tools? A: Extend the server’s src/tools directory and expose them via the MCP manifest; keep tool names short to respect client limits.

Q: Is there CI integration? A: The repository includes Jest tests that can be run in CI pipelines; coverage is output to the coverage folder.

Playwright MCP Server 🎭

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 scraps the page and execute JavaScript in a real browser environment.

Screenshot

Documentation | API reference

Installation

You can install the package using either npm, mcp-get, or Smithery:

Using npm:

npm install -g @executeautomation/playwright-mcp-server

Using mcp-get:

npx @michaellatman/mcp-get@latest install @executeautomation/playwright-mcp-server

Using Smithery

To install Playwright MCP for Claude Desktop automatically via Smithery:

npx @smithery/cli install @executeautomation/playwright-mcp-server --client claude

Installation in VS Code

Install 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.

Configuration to use Playwright Server

Here's the Claude Desktop configuration to use the Playwright server:

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@executeautomation/playwright-mcp-server"]
    }
  }
}

Docker Support

The Playwright MCP Server can be run in Docker for isolated and containerized execution.

Building the Docker Image

Before building the Docker image, you need to build the TypeScript project with production dependencies:

# Install production dependencies and build
npm install --omit=dev
npm run build

# Build the Docker image
docker build -t mcp-playwright .

Or use the provided convenience script:

chmod +x docker-build.sh
./docker-build.sh

Running with Docker

You can run the MCP server using Docker in several ways:

Using Docker directly

# Run the server (stdin/stdout communication)
docker run -i mcp-playwright

Using Docker Compose

A docker-compose.yml file is provided for easier management:

# Run the server with docker-compose
docker compose run --rm playwright-mcp

Using Docker with MCP Clients

To use the Dockerized server with Claude Desktop or other MCP clients, you can configure them to use Docker:

{
  "mcpServers": {
    "playwright": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "mcp-playwright"]
    }
  }
}

Note: The Docker image uses a Debian-based slim Node.js image and includes only the core dependencies. Playwright browsers are not pre-installed in the container to keep the image size small. The browsers will be downloaded on first use if needed.

Testing

This project uses Jest for testing. The tests are located in the src/__tests__ directory.

Running Tests

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.

Running evals

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.ts

Contributing

When 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.

Star History