ApplitoolsをChatGPT、Claude、Geminiに接続

• 01 / 03視覚テストの失敗原因を分析する
• 02 / 03ベースラインの管理方法
• 03 / 03テストバッチの状況を確認する方法

最速日

752ms

最遅日

1178ms

14日間の傾向

遅延傾向+11%

Applitools Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_1ndLMlxAw2nCuJj6kBoTmkGgowFbzClCzzhDWYqC/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Applitools capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "applitools-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_1ndLMlxAw2nCuJj6kBoTmkGgowFbzClCzzhDWYqC/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ ApplitoolsをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  QA自動化エンジニア

  エージェントに未解決のテストバッチの要約を求め、OSやブラウザの特定の失敗パターンを特定する作業に役立ちます。

• 02

  フロントエンド開発者

  PR（プルリクエスト）の際、コンテキストスイッチすることなく、ブランチ固有の視覚ベースラインを検証できます。

• 03

  エンジニアリングマネージャー

  リリース基準が視覚的に満たされているかを確認するため、高レベルなバッチ統計情報を迅速に引き出すことができます。

• 04

  デザイナー

  展開前に、Applitools Visual AIが検出した構造的なUI変更点の概要をエージェントに要求し、確認できます。

• 01

  Does this MCP affect my existing baselines?

  No. The capabilities allow you to list, delete, and manage baselines, but they do not automatically change your existing 'golden' visual standards. You must explicitly authorize the deletion of outdated baselines.

• 02

  Can I see which browsers failed a test?

  Yes. When you request specific session details, the agent can pinpoint the failure, noting the exact OS and browser combination where the visual mismatch occurred.

• 03

  Is this just a report viewer, or can it take action?

  It's more than a viewer. You can ask the agent to perform actions like deleting outdated baselines or discarding legacy test batches, which keeps your workspace clean.

• 04

  What is the difference between a batch and a session?

  A batch groups related test sessions. You first list the batches to get the general status, and then you use the batch ID to get full details of a specific session within that group.

• 05

  Do I need to open the Applitools dashboard to use this?

  No. The entire point of this MCP is to bring the Applitools data into your AI client. You get the analysis and results directly in your chat window.

• 06

  Can my AI agent resolve a test failure on its own?

  No. The MCP server is designed for pulling state data—it retrieves batches, session diff links, and match levels so you can review them locally. Approving a new baseline or resolving a mismatch still requires human intervention within the Applitools Eyes dashboard to maintain absolute testing safety.

• 07

  Can I use the agent to delete old UI snapshots?

  Yes. If your UI has undergone major structural changes and old baselines are causing false positives, you can authorize the agent to execute the delete_baseline capability. Provide the exact baseline ID to instantly discard the legacy screenshot from your workspace.

• 08

  How fast can I summarize test errors after my CI/CD action triggers?

  Almost instantly. Rather than scrolling through dozens of Applitools logs, ask your agent to 'Get batch stats for ID 123'. It will immediately return the aggregation of Passed, Failed, and Unresolved runs, saving you countless minutes of digging.

• 

  Katalon TestOps (AI Test Management) AIコネクタ

  Manage test orchestration via Katalon TestOps — rerun test runs, monitor execution results, and audit software

  表示
• 

  Testim AIコネクタ

  Trigger automated AI tests, inspect execution logs, and manage branches natively via your AI agent.

  表示
• 

  TestRail AIコネクタ

  Browse TestRail suites, parse manual test specs, and monitor active runs seamlessly native within your convers

  表示
• 

  TestMu AI (formerly LambdaTest) AIコネクタ

  Manage cross-browser testing via TestMu AI — audit automation builds, inspect test sessions, and retrieve visu

  表示

おすすめ

• 

  Mabl (AI-Powered Test Automation) AIコネクタ

  Manage E2E testing via Mabl — trigger test plans, monitor execution results, and perform AI-driven failure ana

  表示
• 

  Percy AIコネクタ

  Execute visual regression tests via Percy — track visual diffs natively, inspect snapshot limits, approve buil

  表示
• 

  test-regression-runner AIコネクタ

  Automated verification system that executes targeted test suites and detects regressions or flakiness.

  表示
• 

  TestLink AIコネクタ

  Navigate your self-hosted TestLink instance to inspect test plans, suites, cases, and builds natively via your

  表示