MCP QA Demo Server
Enables natural language-driven browser automation by launching a real browser, performing interactions, and generating test artifacts like feature/step/page files.
README
MCP QA Demo
This project demonstrates the difference between:
- general automation: execute a browser flow with Playwright + Cucumber
- MCP-assisted automation: run the same flow and then invoke an MCP tool for analysis
1. Setup on another machine
Prerequisites
- Node.js 18+ installed
- npm installed
- Internet access for downloading Playwright browsers
Install dependencies
git clone <your-repo-url>
cd mcp-qa-demo
npm install
npx playwright install
VS Code MCP setup
- Open the workspace in VS Code.
- Make sure the folder contains .vscode/mcp.json.
- Restart VS Code or reload the window.
- Open Copilot Chat and use the MCP server from the workspace.
2. Run the general flow
npm run test:general
3. Run the MCP flow
npm run test:mcp
4. Run both flows back to back
npm run demo:both
5. Start the MCP server directly
npm run mcp:server
6. How to use it
- Start the MCP server:
npm run mcp:server
- In Claude or another MCP-compatible chat client, send a prompt such as:
Open Google and search for automation demo
-
The MCP tool exposed by this server will launch a real browser, perform the interaction, and generate the feature/step/page artifacts.
-
The generated files will be written under the generated folder.
7. TypeScript prompt runner
You can also try a prompt-driven browser flow directly in TypeScript:
node -r ts-node/register/transpile-only src/demo.ts "open google and search for automation demo"
8. Quick demo summary
- Traditional automation: write scripts manually and execute them.
- MCP automation: describe the task in chat, let the tool observe the browser, and generate the automation assets.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.