Playwright MCP Server

Created By
san0808a year ago
This server provides a comprehensive set of tools to control a web browser instance using Playwright, exposed via the Model Context Protocol (MCP). It allows AI models or other MCP clients to perform complex web browsing tasks across multiple pages/tabs.
Overview

What is Playwright MCP Server?

Playwright MCP Server is a tool that allows users to control web browser instances using Playwright, facilitating complex web browsing tasks through the Model Context Protocol (MCP).

How to use Playwright MCP Server?

To use the server, install the necessary dependencies and Playwright browsers, then run the server using the command python main.py. You can also run it with Server-Sent Events (SSE) on a specified port.

Key features of Playwright MCP Server?

  • Multi-Page Management: Open, close, and switch between multiple browser pages/tabs.
  • Robust Lifecycle Management: Reliable setup and teardown of Playwright resources.
  • Comprehensive Tools: Includes page management, navigation, content retrieval, interaction, waiting, state information, visuals, and JavaScript evaluation.

Use cases of Playwright MCP Server?

  1. Automating web testing across multiple pages.
  2. Scraping data from websites efficiently.
  3. Performing complex interactions on web applications.

FAQ from Playwright MCP Server?

  • Can I control multiple pages at once?

Yes! The server supports managing multiple pages/tabs simultaneously.

  • Is it safe to use JavaScript evaluation tools?

Use caution as these tools can be dangerous if the server is exposed publicly. It's advisable to disable them if security is a concern.

  • What programming language is used?

The server is implemented in Python.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
san0808
Star
0
Language
Python
License
MIT license
Tags

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 minutes ago