MCP End-to-End Testing for Roo-Code Integration

@shipdocs

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

shipdocs

MCP End-to-End Testing for Roo-Code Integration について

This runs a mcp server for automatic testing of usability from a users pov

MCP End-to-End Testing for Roo-Code Integration の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "vibe-coding-mcp-end-2-end-testing": {
      "command": "node",
      "args": [
        "index.js"
      ]
    }
  }
}

MCP End-to-End Testing for Roo-Code Integration のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP End-to-End Testing for Roo-Code Integration?

This repository provides an MCP (Model Context Protocol) server, published as the npm package @shipdocs/mcp-playwright-test, for automated web testing using Playwright. It is designed to integrate with VSCode AI extensions like Roo-Code, enabling AI-assisted browser automation, error detection, and debugging.

How to use MCP End-to-End Testing for Roo-Code Integration?

Install the package globally with npm install -g @shipdocs/mcp-playwright-test, then initialize a configuration file with mcp-playwright-test init and start the server with mcp-playwright-test start. On first run you will be prompted to configure login details for your target website. Alternatively, clone the repository and run node index.js from the mcp-playwright-test directory. To integrate with Roo-Code, add a new MCP server in VSCode using STDIO or SSE transport.

Key Features of MCP End-to-End Testing for Roo-Code Integration

Full MCP server with resource and command endpoints
Playwright-powered browser automation for Chrome, Firefox, and WebKit
Automated login, navigation, and web exploration
Error detection and logging for AI-assisted debugging
Screenshot capture and accessibility analysis
STDIO and SSE transport for Roo-Code integration

Use Cases of MCP End-to-End Testing for Roo-Code Integration

Run automated end-to-end tests with AI guidance via Roo-Code
Test login flows and multi-page navigation in web applications
Capture screenshots and analyze accessibility for QA workflows
Enable AI assistants to debug web pages interactively
Integrate browser testing into VSCode-based AI coding sessions

よくある質問

What is the difference between this MCP server and a standalone Playwright script?

This server implements the Model Context Protocol, allowing AI assistants like Roo-Code to control browser actions, retrieve test results, and debug through a standardized interface rather than running isolated scripts.

What are the runtime dependencies?

Node.js and npm are required. Playwright browsers (Chromium, Firefox, WebKit) are automatically managed by the Playwright library when starting the server.

How is user data or login information handled?

On first run, the tool prompts you to configure login details for your target website. Configuration is stored locally in a file created by the `init` command.

What transports are supported for Roo-Code integration?

Both STDIO (run the tool as a child process) and SSE (connect to an already running server) transports are supported, configurable through Roo-Code MCP settings in VSCode.

Are there any known limitations?

The README does not document specific limitations. It references detailed user and integration guides for advanced configuration.

「開発者ツール」の他のコンテンツ

GAIP Agents

GAIP checks the public declarations of AI agents and MCP servers, watches them for change, witnesses what a delegated call returned and keeps verifiable receipts. Free, read-only, no account or API key. Every result sta

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Termany

thinkany-ai

Agent-Native Terminal

174

TaskerArmy Agent

TaskerArmy

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.