About mcp-server-playwright
mcp-server-playwright is an experimental MCP server for controlling a browser with Playwright, aimed at AI-driven browser operation. It supports navigation, tab management, and extracting readable content from the current page.
Key features
- 01Open and close the browser
- 02Navigate to a URL
- 03Open pages in new tabs
- 04Close a specified page
- 05Extract readable page content
Use cases
- 01Open and browse sites through AI
- 02Extract readable content from the current page
MCP support
The MCP server exposes Playwright browser-control tools to MCP clients, including browser lifecycle, navigation, and content extraction.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-server-playwright
This project is an experimental project aimed at manipulating a browser through MCP using Playwright, in order to implement a feature to control the browser through AI.
Tools
- open-browser(url) : Open a browser with the specified URL(option).
- close-page(pageNumber: int) : Close a desiginated page in current browser.
- close-browser() : Close the browser.
- navigate-to-page(url) : Navigate to the specified URL.
- open-new-page(url) : Open a page in a new tab.
- get-page-content() : Get the readability content of the current page.
Usage
Install dependencies
- bun
- pnpm
pnpm install
MCP Configuration
{
"mcpServers": {
"mcp-server-playwright": {
"command": "bun",
"args": ["yourpath/mcp-server-playwright/src/index.ts"],
"env": {
"CHROME_PATH": "your_chrome_path",
"MUSER_DATA_DIR": "your_chrome_user_data_path"
}
}
}
}
Have fun!
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.