End to End testing MCP Server

enedtoend-demo.1.mp4

A Model Context Protocol (MCP) server powered by Playwright that provides automated end-to-end testing with dedicated LLM-driven test validation, separating testing concerns from the MCP client.

Note: This MCP is forked from Microsoft's Playwright MCP. We optimized Playwright MCP for automated end to end testing.

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

• Automated testing driven by LLMs

Example config

After cloning this repo, build and add the E2E MCP server to your MCP Client as such: Notice that you need OpenAI API key to run this MCP server in end to end mode.

npm install
npx playwright install
npm run build

Then:

{
    "mcpServers": {
        "e2e": {
            "command": "node",
            "args": [
                "/Users/Documents/projects/e2e-mcp/lib/program.js",
                "--endtoend",
                "--api-key=<your openai api key>"
            ]
        }
    }
}

User data directory

E2E MCP will launch Chrome browser with the new profile, located at

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

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