Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AIAgentMCP navigate to example.com and take a screenshot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A minimal Playwright project scaffold for automated testing and Model Context Protocol (MCP) development.
This repository includes:
Playwright test setup using @playwright/test
Example browser tests in tests/
A sample Playwright MCP workflow via npm run mcp
Docker install helper script at ../install-docker.ps1 for Windows environments
Related MCP server: Playwright MCP Server
cd AIAgentMCP
npm installnpm run testnpm run mcppackage.json / package-lock.json — project dependencies and scripts
playwright.config.ts — Playwright configuration
tests/ — sample Playwright tests
test-results/ — test output and artifacts
.gitignore — ignored files for this repository
The project uses @playwright/test as a dev dependency.
The mcp script launches Playwright MCP using npx @playwright/mcp@latest.
On Windows, Docker Desktop is required for many Playwright workflows that use containers.
This server cannot be deployed
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Launch, inspect, control, and share isolated cloud browsers for your agents.
Headless browser primitives for AI agents when sites need real JS rendering.
