How do I connect my Mabl account?

You subscribe to the MCP on Vinkius and enter your Mabl API Key. Once connected, your AI client can immediately access your Mabl data.

Which AI clients can I use with this MCP?

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

Can I trigger tests in specific environments?

Yes, you can trigger test plans in specific environments like staging or production through your agent.

Does this MCP provide visual debugging?

Yes, the agent can retrieve detailed failure analysis and screenshots from Mabl executions to help you debug UI issues.

Can I manage API tests with this capability?

Yes, the MCP includes capabilities to list and manage your Mabl API tests.

Can I see exactly why a Mabl test failed using my agent?

Yes. Use the mb.get_execution capability with a specific Execution ID. Your agent will retrieve deep diagnostic information, including the failure reason, test outcomes, and visual screenshots to help you identify UI regressions instantly.

How do I trigger a specific test plan through a conversation?

The mb.trigger_plan capability allows your agent to start executions associated with a Plan ID or Label. You can also specify an optional Environment ID to target a specific stage (e.g., Staging vs Prod) for your automated tests.

Can my agent list all available testing environments in my account?

Absolutely. Use the mb.list_envs capability to identify all configured environments. Your agent will report the environment names, IDs, and any associated environment variables defined in Mabl.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Mabl AI Powered Test Automation to your AI

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 E2E test suites through your AI agent.

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.

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.

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 Mabl.

01
Mb.get execution
This capability retrieves full details for a specific Mabl execution. It provides status, duration, test outcomes, failure analysis, and screenshots.
02
Mb.list envs
This capability lists all configured Mabl environments. It returns environment names, IDs, and associated variables.
03
Mb.list executions
This capability fetches the most recent execution results from your Mabl account.
04
Mb.list labels
This capability retrieves all labels used in your Mabl plans. It shows label names and how many plans are associated with each.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Mabl.

05
Mb.list plans
This capability lists your Mabl test plans. It returns plan names, statuses, triggers, and linked applications or environments.
06
Mb.trigger plan
This capability starts a Mabl plan run based on a deployment event.
07
Mb.workspace info
This capability pulls metadata for your authenticated Mabl workspace, including the organization and workspace name.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Mabl.

08
Mb.get app
This capability fetches specific details for a Mabl application, such as its name, description, target URLs, and labels.
09
Mb.list apps
This capability lists all applications currently monitored in your Mabl account.
10
Mb.list tests
This capability retrieves a list of all API tests configured in Mabl.

Real work

What teams actually run

Regression Testing

Trigger a full regression suite after a new deployment to ensure stability.

Rapid Debugging

Ask your agent for the reason a specific test failed to find the root cause immediately.

Environment Validation

Check that your staging environment variables are correctly set before running tests.

API Health Checks

Monitor the status of your API tests to ensure backend services are functioning.

Automate a task

Put Mabl 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

Mabl 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.

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

You don't need a client to put Mabl 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

959ms average. Fast in production.

Mabl is checked daily against the live service.

Daily averagePeak 1156ms

Oct 3Today

Fastest day: 764ms
Slowest day: 1156ms
14-day trend: Slowing+7%

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

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

Mabl Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_GzAfS6LnIq6mGDl04Utu0UzYyZgbblzxeJf9xvxR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

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

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "mabl-ai-powered-test-automation-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_GzAfS6LnIq6mGDl04Utu0UzYyZgbblzxeJf9xvxR/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 Mabl in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Mabl owners hand off.

This MCP is built for technical teams managing automated quality assurance workflows.

01
QA Automation Engineers
They use the agent to trigger complex test suites and analyze failure diagnostics.
02
Software Developers
They use the agent to verify build quality and pull UI regression screenshots.
03
DevOps Teams
They use the agent to audit CI/CD results and monitor environment health.

FAQ

Questions Mabl owners ask.

01
How do I connect my Mabl account?
You subscribe to the MCP on Vinkius and enter your Mabl API Key. Once connected, your AI client can immediately access your Mabl data.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.
03
Can I trigger tests in specific environments?
Yes, you can trigger test plans in specific environments like staging or production through your agent.
04
Does this MCP provide visual debugging?
Yes, the agent can retrieve detailed failure analysis and screenshots from Mabl executions to help you debug UI issues.
05
Can I manage API tests with this capability?
Yes, the MCP includes capabilities to list and manage your Mabl API tests.
06
Can I see exactly why a Mabl test failed using my agent?
Yes. Use the mb.get_execution capability with a specific Execution ID. Your agent will retrieve deep diagnostic information, including the failure reason, test outcomes, and visual screenshots to help you identify UI regressions instantly.
07
How do I trigger a specific test plan through a conversation?
The mb.trigger_plan capability allows your agent to start executions associated with a Plan ID or Label. You can also specify an optional Environment ID to target a specific stage (e.g., Staging vs Prod) for your automated tests.
08
Can my agent list all available testing environments in my account?
Absolutely. Use the mb.list_envs capability to identify all configured environments. Your agent will report the environment names, IDs, and any associated environment variables defined in Mabl.

Explore

More in Developer Tools

Connect Mabl to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Mb.get execution

Mb.list envs

Mb.list executions

Mb.list labels

05-07

Mb.list plans

Mb.trigger plan

Mb.workspace info

08-10

Mb.get app

Mb.list apps

Mb.list tests

What teams actually run

Regression Testing

Rapid Debugging

Environment Validation

API Health Checks

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

Mabl Connector

Claude Desktop

QA Automation Engineers

Software Developers

DevOps Teams

How do I connect my Mabl account?

Which AI clients can I use with this MCP?

Can I trigger tests in specific environments?

Does this MCP provide visual debugging?

Can I manage API tests with this capability?

Can I see exactly why a Mabl test failed using my agent?

How do I trigger a specific test plan through a conversation?

Can my agent list all available testing environments in my account?

Katalon TestOps (AI Test Management) AI Connector

Codecov AI Connector

Testim AI Connector

TestRail AI Connector

Suggestions

Sauce Labs AI Connector

Cypress Cloud AI Connector

TestLink AI Connector

BrowserStack AI Connector