Playwright

Provides a Playwright-based MCP server with note storage and automation tools for navigating pages, taking screenshots, and summarizing notes.
  • other

0

GitHub Stars

other

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": {
    "mcp-mirror-williamvd4_playwright-plus-python-mcp": {
      "command": "uvx",
      "args": [
        "playwright-server"
      ]
    }
  }
}

You run an MCP server that automates browser tasks with Playwright and stores simple notes. It lets you navigate to pages, capture screenshots, interact with page elements, and generate summaries of your notes. This makes it easy to build automated testing or content-inspection workflows that statefully manage a collection of notes and observations.

How to use

Install and run the server, then connect an MCP client to exercise its features. You can store notes with a name, description, and text content. Use the available tools to navigate to URLs, click elements, fill inputs, capture screenshots, and run JavaScript in the page context. You can also generate summaries of all stored notes using the summarize-notes prompt.

How to install

Prerequisites: you need a runtime able to execute MCP servers, typically via the MCP runtime tools. You will also need a local directory to run the server from.

{
  "mcpServers": {
    "playwright_server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "playwright-server"
      ]
    }
  }
}

Additional configuration and startup notes

The server exposes a set of resources and prompts, plus a collection of tools that you can invoke from your MCP client. No additional environment variables are required to run the server by default.

Notes on development and debugging

When debugging, you can use the MCP Inspector to trace interactions and inspect runtime state. Start the server normally and then attach the inspector to view the live session URL.

Available tools

playwright_navigate

Navigates to a specified URL and automatically creates a new session if none exists.

playwright_screenshot

Takes a screenshot of the current page or a specific element. Requires a name for the screenshot file and an optional CSS selector.

playwright_click

Clicks an element on the page using a CSS selector. Requires a selector to identify the element.

playwright_fill

Fills out an input field. Requires a selector for the input and the value to insert.

playwright_evaluate

Executes JavaScript code in the browser console for dynamic interaction or querying page state.

playwright_click_text

Clicks an element on the page by matching its visible text content.

playwright_get_text_content

Retrieves the text content of all visible elements on the page.

playwright_get_html_content

Gets the HTML content of a specified element using a CSS selector.

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