An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Testim 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. Run and debug end-to-end test suites without leaving your IDE.

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 Testim.

  1. 01

    List project branches

    This capability shows you all the parallel development branches currently in your Testim project.

  2. 02

    List tests

    Use this to get a full list of every automated test within your Testim project.

  3. 03

    Get test details

    This capability pulls the complete technical details for a specific Testim test.

  4. 04

    Merge project branch

    This capability merges test changes from one branch into another, such as moving feature changes into master.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Testim.

  1. 05

    Get execution results

    Use this to check the pass or fail status and specific results of a test execution.

  2. 06

    Run tests by label

    This capability triggers a new run for every test that matches a specific label you provide.

  3. 07

    Run test plan

    Use this to start a run for a predefined Testim test plan.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Testim.

  1. 08

    Run specific test

    This capability starts an immediate run for a single test and returns an execution ID.

  2. 09

    Run test suite

    Use this to trigger a run for every test contained within a specific suite.

  3. 10

    Create project branch

    This capability creates a new branch for test development within your project.

Real work

What teams actually run

01

Immediate Regression Testing

A QA engineer triggers a full suite run via chat immediately after a new environment deployment.

02

In-IDE Verification

A developer runs a specific E2E test script inside Cursor to check a UI fix before committing.

03

Deployment Auditing

A release manager asks the agent for the status of a specific execution ID to verify a build.

04

Branch Synchronization

A developer merges a feature branch into the master branch using a simple command.

Automate a task

Put Testim 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

Testim 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 Testim 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

899ms average. Fast in production.

Testim is checked daily against the live service.

Daily averagePeak 1181ms
Oct 3Today
Fastest day
705ms
Slowest day
1181ms
14-day trend
Slowing+32%

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 Testim, so you can see the experience inside your AI.

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

Testim Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_dV0W5EQeoJdAE8PdakI0g1dIqsqeDyfRO2hc7Oq6/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 — Testim capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "testim-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_dV0W5EQeoJdAE8PdakI0g1dIqsqeDyfRO2hc7Oq6/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 Testim in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Testim owners hand off.

This MCP is built for technical teams who need to manage automated testing without leaving their development environment.

  • 01

    QA Engineers

    They use the agent to trigger full regression suites as soon as environments are ready.

  • 02

    Frontend Developers

    They run specific E2E scripts directly inside their IDE to verify code changes.

  • 03

    Release Managers

    They use the agent to audit test plan health and confirm green lights before deployment.

FAQ

Questions Testim owners ask.

  • 01

    How do I connect this MCP to my Testim project?

    You need to subscribe to the MCP on Vinkius and then provide your Testim Project ID and API Key when prompted.

  • 02

    Which AI clients can I use with this?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I run tests on specific branches?

    Yes, you can create branches, list them, and trigger runs on specific branches through your agent.

  • 04

    How do I see why a test failed?

    You can ask your agent to retrieve the execution results or diagnostic summaries for a specific execution ID.

  • 05

    Does this replace the Testim web interface?

    It doesn't replace it, but it allows you to perform most common orchestration and diagnostic tasks without opening the GUI.

  • 06

    Can my AI agent actually trigger test runs remotely?

    Yes! You can ask your agent to list your available tests, pick an ID, and say 'Run this sequence'. Testim's dynamic runner architecture handles the load while your AI returns the execution ID for you to track.

  • 07

    How can it help me troubleshoot a failed test run?

    Typically, you'd open the Testim dashboard, navigate to the specific test suite run, and read the logs. With this integration, you just instruct the agent to retrieve results for that specific Execution ID; it will summarize error strings immediately in markdown.

  • 08

    Can I merge test changes through the agent?

    Absolutely. Because Testim supports branching, your agent can act as a command terminal. Ask to list branches, select a recently updated feature branch, and say 'Merge branch feature-login into master'.

Explore

More in Developer Tools

Suggestions

Connect Testim to Claude, Cursor, ChatGPT & more