How to Use the Mabl (AI-Powered Test Automation) MCP in Claude Code

Q: How can I use Claude Code to trigger a Mabl (AI-Powered Test Automation) plan from a shell script?

After connecting the MCP server, you can run claude tool mb.triggerplan --planid=. This command will start the Mabl test plan and return the deployment event ID, which you can use to track the run.

Q: Can I poll for test results from Mabl (AI-Powered Test Automation) in a CI pipeline using Claude Code?

Yes. After triggering a plan, you can use a while loop in your CI script to call claude tool mb.getexecution. Check the 'status' field in the JSON output to decide whether to continue the deployment or fail the build.

Q: What's the command to list all Mabl environments with Claude Code?

The command is claude tool mb.listenvs. It will return a JSON array containing the names, IDs, and any configured environment variables for all environments in your Mabl workspace.

Plug Mabl's AI-powered testing directly into your deployment scripts and CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mabl (AI-Powered Test Automation) MCP to Claude Code

Create your Vinkius account to connect Mabl (AI-Powered Test Automation) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mabl (AI-Powered Test Automation) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Gate Deployments with Test Results

This is how you automate release gating. Add a step in your GitHub Action or Jenkinsfile that uses Claude Code to call `mb.trigger_plan`. This kicks off your Mabl regression suite against the new build. The script then simply polls `mb.get_execution` in a loop. If the tests pass, the deployment proceeds. If they fail, the script exits with an error, stopping a bad deploy in its tracks. No human intervention required.

Automate Test Health Reporting

Get a daily pulse on your application's quality. Set up a simple cron job that uses Claude Code to run `mb.list_executions` every morning for your main branch. You can pipe the JSON output to `jq` to filter for failures. From there, you can format a summary and post it to a Slack channel or send an email. The whole process is a few lines in a shell script, giving you a fully automated daily quality report.

Script Your Mabl Test Infrastructure

Don't manage your test setup by hand. Write scripts with Claude Code to audit your Mabl workspace. Use `mb.list_plans` and `mb.list_labels` to enforce naming conventions or check for untagged tests. You can also use `mb.list_apps` and `mb.list_envs` to programmatically verify that your non-production environments match the production config. This MCP integration makes your Mabl workspace another piece of auditable, scriptable infrastructure.

Setup guide

Set up Mabl (AI-Powered Test Automation) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see mabl-ai-powered-test-automation-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Mabl (AI-Powered Test Automation) transactions." It will automatically discover and invoke the available Mabl (AI-Powered Test Automation) tools.

Terminal

claude mcp add --transport http mabl-ai-powered-test-automation-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Mabl (AI-Powered Test Automation) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "mabl-ai-powered-test-automation-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mabl. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Mabl (AI-Powered Test Automation) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Mabl (AI-Powered Test Automation) MCP in Claude Code

After connecting the MCP server, you can run `claude tool mb.trigger_plan --plan_id=`. This command will start the Mabl test plan and return the deployment event ID, which you can use to track the run.

Yes. After triggering a plan, you can use a `while` loop in your CI script to call `claude tool mb.get_execution`. Check the 'status' field in the JSON output to decide whether to continue the deployment or fail the build.

The command is `claude tool mb.list_envs`. It will return a JSON array containing the names, IDs, and any configured environment variables for all environments in your Mabl workspace.

Absolutely. Since Claude Code is a terminal client, you can run it inside any Docker container that has a shell. This is a common pattern for creating reproducible, isolated testing environments in CI/CD.

Your Mabl API key and other credentials are not exposed to the client. Vinkius manages authentication through a single, revocable token for the MCP server. All data in transit, like plan names and execution logs, is encrypted, and the server runs in a secure, single-use sandbox.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript