ExecuteAutomation Playwright MCP

An MCP server with a browser action recorder that generates ready-to-run Playwright test files.

MCP ServerMCP-Compatible AgentsVerified

View source

Category: Test Automation
Author: executeautomation
Pricing: free

Connect ExecuteAutomation Playwright MCP to your agent

claude mcp add --transport stdio executeautomation-playwright -- npx @executeautomation/playwright-mcp-server

Add the server
Run this command in your terminal.
Finish setup
Claude Code starts this server locally. Restart Claude Code and retry if the server does not appear.
Try it
Ask your agent: “Open example.com and take a screenshot.”

{
  "mcpServers": {
    "executeautomation-playwright": {
      "command": "npx",
      "args": [
        "@executeautomation/playwright-mcp-server"
      ]
    }
  }
}

Add the server
Add this configuration to Cursor's user-level or project-level mcp.json.
Finish setup
Enable the server in Cursor's MCP settings. Restart Cursor and retry if the server does not appear.
Try it
Ask your agent: “Open example.com and take a screenshot.”

codex mcp add executeautomation-playwright -- npx @executeautomation/playwright-mcp-server

Add the server
Run this command in your terminal.
Finish setup
Codex starts this server locally. Restart Codex and retry if the server does not appear.
Try it
Ask your agent: “Open example.com and take a screenshot.”

{
  "mcpServers": {
    "executeautomation-playwright": {
      "command": "npx",
      "args": [
        "@executeautomation/playwright-mcp-server"
      ]
    }
  }
}

Add the server
Add this configuration to your client's MCP configuration file.
Finish setup
Save the configuration and restart your client if the server does not appear.
Try it
Ask your agent: “Open example.com and take a screenshot.”

What it does

ExecuteAutomation Playwright MCP is an MCP server that gives LLMs and AI assistants browser automation via Playwright — interacting with pages, taking screenshots, executing JavaScript, web-scraping, and generating test code. It ships codegen tools (start_codegen_session, end_codegen_session, get_codegen_session, clear_codegen_session) where an action recorder captures browser actions and emits a complete Playwright test file with standard test()/async ({page}) structure and a configurable output path. It integrates with Claude Code, Claude Desktop, Cursor, and Cline.

How QA teams use it

Start a codegen session, walk through a flow in the browser via the AI assistant, and end the session to get a runnable Playwright spec file.
Use the same MCP connection for screenshots, JavaScript execution, and lightweight web scraping during exploratory checks.
Drop the generated spec straight into a Playwright test suite since it follows the standard test file structure.