Playwright

Provides browser automation via Playwright MCP server with structured data for integration with AI tools and editors.
  • javascript

0

GitHub Stars

javascript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "faruklmu17-playwright_mcp": {
      "command": "npx",
      "args": [
        "playwright-mcp",
        "--port",
        "3550"
      ]
    }
  }
}

You can automate and inspect web pages using a dedicated MCP server that runs Playwright commands and exposes structured data. This lets you integrate browser automation with tools and IDEs without relying on screenshots, enabling powerful workflows for AI assistants and development assistants.

How to use

Launch the MCP server from your development environment and connect your MCP-compatible client (such as a code editor or AI-assisted tool). Once running, your client can issue browser automation commands through the MCP interface and receive structured data about pages, elements, and interactions. You can run the server with different port settings to fit your local or team setup, and you can opt for persistent or isolated browser sessions depending on your testing or automation needs.

How to install

Prerequisites: Node.js v18 or newer.

Install the MCP server dependencies and start the server.

npm install
npx playwright-mcp --port 3550

Configuration and usage notes

The server is designed to be launched by a client. Use the following example to configure a client to connect to the running MCP server on port 3550.

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "playwright-mcp",
        "--port=3550"
      ]
    }
  }
}

Additional notes

You can customize the port with --port, enable headless mode, emulate devices, or enable vision features if supported. The MCP server handles browser automation setup so you don’t need to install or configure browser binaries separately.

Troubleshooting and tips

If the server doesn’t start, verify that Node.js is installed and that port 3550 (or your chosen port) is not in use. Check that you used the correct command: npx playwright-mcp --port 3550. If you want a persistent session, configure the client accordingly to reuse the same browser state across connections.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational