An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Applitools to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Analyze UI changes and test health without leaving your chat window.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Applitools.

  1. 01

    Get batch stats

    Returns passed/failed/unresolved/new counts without full test data. Get summary statistics for an Applitools batch

  2. 02

    List baselines

    Returns baseline IDs, names, and env configs. Filter by app name. List visual baselines for an app on Applitools

  3. 03

    List batches

    Batches group related test sessions. Returns batch IDs, names, statuses (Passed/Unresolved/Failed), and test counts. Each batch has a unique ID used to query its results. List all test batches on Applitools Eyes

  4. 04

    List branch baselines

    Use to inspect branch-specific visual states. List baselines for a specific branch on Applitools

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Applitools.

  1. 05

    Delete baseline

    Use when a baseline is outdated or a page has been redesigned. Delete an Applitools test baseline

  2. 06

    Delete batch

    Does NOT affect baselines. Use with caution. this is irreversible. Delete an Applitools test batch

  3. 07

    Get batch

    Use batch ID from list_batches. Get full details of an Applitools batch

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Applitools.

  1. 08

    Get session

    Provide batch ID and session ID. Get details of a test session within an Applitools batch

  2. 09

    List results

    List all test results in an Applitools batch

  3. 10

    Validate key

    Use to verify connectivity before running tests. Validate the Applitools API key

Real work

What teams actually run

01

Pre-Release Validation

Before a major release, ask your agent to list all baselines for the main branch. This confirms that all critical visual components are accounted for.

02

Pull Request Review

A developer pushes a PR. You ask the agent to list baselines specific to that branch to verify the visual impact of the changes.

03

Debugging Failures

When a test fails, you ask the agent to get the full session details. It identifies the exact step, the browser, and the type of visual mismatch.

04

Data Housekeeping

The team has accumulated old test data. You ask the agent to delete outdated baselines or old batches to prevent data clutter.

Automate a task

Put Applitools to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Applitools works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Applitools to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

936ms average. Fast in production.

Applitools is checked daily against the live service.

Daily averagePeak 1178ms
Oct 3Today
Fastest day
752ms
Slowest day
1178ms
14-day trend
Slowing+11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Applitools, so you can see the experience inside your AI.

It does not authenticate your account with Applitools. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Applitools Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_1ndLMlxAw2nCuJj6kBoTmkGgowFbzClCzzhDWYqC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  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.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "applitools-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_1ndLMlxAw2nCuJj6kBoTmkGgowFbzClCzzhDWYqC/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Applitools in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Applitools owners hand off.

This MCP is essential for teams that rely on visual quality assurance. If your job involves verifying that a UI change looks correct across multiple browsers and devices, this connector gives your AI agent the data it needs to act.

  • 01

    QA Automation Engineers

    Ask your agent to summarize unresolved test batches and pinpoint exact OS/browser failure combinations.

  • 02

    Frontend Developers

    Verify branch-specific visual baselines during PRs without having to switch context to the Applitools dashboard.

  • 03

    Engineering Managers

    Pull high-level batch statistics to ensure that release criteria are visually met before deployment.

  • 04

    Designers

    Request a quick breakdown of structural UI changes caught by Applitools Visual AI before the code goes live.

FAQ

Questions Applitools owners ask.

  • 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.

Explore

More in Ship It

Suggestions

Connect Applitools to Claude, Cursor, ChatGPT & more