MCP 服务器

Playwright MCP

Provides browser automation capabilities for LLMs using Playwright, leveraging structured accessibility snapshots to interact with web pages without needing vision models. It enables tasks like web navigation, data extraction, and automated testing through a lightweight and deterministic toolset.

README

Playwright MCP

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

Key Features

Fast and lightweight: Uses Playwright's accessibility tree, not pixel-based input.
LLM-friendly: No vision models needed, operates purely on structured data.
Deterministic tool application: Avoids ambiguity common with screenshot-based approaches.

Use Cases

Web navigation and form-filling
Data extraction from structured content
Automated testing driven by LLMs
General-purpose browser interaction for agents

Example config

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@hyhfish/mcp-hyh@latest"
      ]
    }
  }
}

Installation in VS Code
Command line
User profile
Configuration file
Running on Linux
Docker
Programmatic usage
Tool modes

Installation in VS Code

You can install the Playwright MCP server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"playwright","command":"npx","args":["@hyhfish/mcp-hyh@latest"]}'

After installation, the Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.

Command line

The Playwright MCP server supports the following command-line options:

--browser <browser>: Browser or chrome channel to use. Possible values:
- chrome, firefox, webkit, msedge
- Chrome channels: chrome-beta, chrome-canary, chrome-dev
- Edge channels: msedge-beta, msedge-canary, msedge-dev
- Default: chrome
--caps <caps>: Comma-separated list of capabilities to enable, possible values: tabs, pdf, history, wait, files, install. Default is all.
--cdp-endpoint <endpoint>: CDP endpoint to connect to
--executable-path <path>: Path to the browser executable
--headless: Run browser in headless mode (headed by default)
--device: Emulate mobile device
--user-data-dir <path>: Path to the user data directory
--port <port>: Port to listen on for SSE transport
--host <host>: Host to bind server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.
--allowed-origins <origins>: Semicolon-separated list of origins to allow the browser to request. Default is to allow all. Origins matching both --allowed-origins and --blocked-origins will be blocked.
--blocked-origins <origins>: Semicolon-separated list of origins to block the browser to request. Origins matching both --allowed-origins and --blocked-origins will be blocked.
--vision: Run server that uses screenshots (Aria snapshots are used by default)
--output-dir: Directory for output files
--config <path>: Path to the configuration file

User profile

Playwright MCP will launch the browser with the new profile, located at

- `%USERPROFILE%\AppData\Local\ms-playwright\mcp-{channel}-profile` on Windows
- `~/Library/Caches/ms-playwright/mcp-{channel}-profile` on macOS
- `~/.cache/ms-playwright/mcp-{channel}-profile` on Linux

All the logged in information will be stored in that profile, you can delete it between sessions if you'd like to clear the offline state.

Configuration file

The Playwright MCP server can be configured using a JSON configuration file. Here's the complete configuration format:

{
  // Browser configuration
  browser?: {
    // Browser type to use (chromium, firefox, or webkit)
    browserName?: 'chromium' | 'firefox' | 'webkit';

    // Path to user data directory for browser profile persistence
    userDataDir?: string;

    // Browser launch options (see Playwright docs)
    // @see https://playwright.dev/docs/api/class-browsertype#browser-type-launch
    launchOptions?: {
      channel?: string;        // Browser channel (e.g. 'chrome')
      headless?: boolean;      // Run in headless mode
      executablePath?: string; // Path to browser executable
      // ... other Playwright launch options
    };

    // Browser context options
    // @see https://playwright.dev/docs/api/class-browser#browser-new-context
    contextOptions?: {
      viewport?: { width: number, height: number };
      // ... other Playwright context options
    };

    // CDP endpoint for connecting to existing browser
    cdpEndpoint?: string;

    // Remote Playwright server endpoint
    remoteEndpoint?: string;
  },

  // Server configuration
  server?: {
    port?: number;  // Port to listen on
    host?: string;  // Host to bind to (default: localhost)
  },

  // List of enabled capabilities
  capabilities?: Array<
    'core' |    // Core browser automation
    'tabs' |    // Tab management
    'pdf' |     // PDF generation
    'history' | // Browser history
    'wait' |    // Wait utilities
    'files' |   // File handling
    'install' | // Browser installation
    'testing'   // Testing
  >;

  // Enable vision mode (screenshots instead of accessibility snapshots)
  vision?: boolean;

  // Directory for output files
  outputDir?: string;

  // Network configuration
  network?: {
    // List of origins to allow the browser to request. Default is to allow all. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
    allowedOrigins?: string[];

    // List of origins to block the browser to request. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
    blockedOrigins?: string[];
  };
 
  /**
   * Do not send image responses to the client.
   */
  noImageResponses?: boolean;
}

You can specify the configuration file using the --config command line option:

npx @hyhfish/mcp-hyh@latest --config path/to/config.json

Running on Linux

When running headed browser on system w/o display or from worker processes of the IDEs, run the MCP server from environment with the DISPLAY and pass the --port flag to enable SSE transport.

npx @hyhfish/mcp-hyh@latest --port 8931

And then in MCP client config, set the url to the SSE endpoint:

{
  "mcpServers": {
    "playwright": {
      "url": "http://localhost:8931/sse"
    }
  }
}

Docker

NOTE: The Docker implementation only supports headless chromium at the moment.

{
  "mcpServers": {
    "playwright": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--init", "--pull=always", "mcr.microsoft.com/playwright/mcp"]
    }
  }
}

You can build the Docker image yourself.

docker build -t mcr.microsoft.com/playwright/mcp .

Programmatic usage

import http from 'http';

import { createServer } from '@hyhfish/mcp-hyh';
import { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';

http.createServer(async (req, res) => {
  // ...

  // Creates a headless Playwright MCP server with SSE transport
  const connection = await createConnection({ browser: { launchOptions: { headless: true } } });
  const transport = new SSEServerTransport('/messages', res);
  await connection.connect(transport);

  // ...
});

Tool modes

The tools are available in two modes:

Snapshot Mode (default): Uses accessibility snapshots for better performance and reliability
Vision Mode: Uses screenshots for visual-based interactions

To use Vision Mode, add the --vision flag when starting the server:

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@hyhfish/mcp-hyh@latest",
        "--vision"
      ]
    }
  }
}

Vision Mode works best with the computer use models that are able to interact with elements using X Y coordinate space, based on the provided screenshot.