How to Use the Mabl (AI-Powered Test Automation) MCP in OpenAI Agents SDK

Q: Can I run specific test plans via Mabl (AI-Powered Test Automation) with OpenAI Agents SDK?

Yes, you can. Your agent can query available runs with mb.listplans and then execute them using mb.triggerplan. This allows the agent to target specific environments and labels dynamically based on your deployment context.

Q: How does the Mabl (AI-Powered Test Automation) MCP integration handle test failures in OpenAI Agents SDK?

The agent uses mb.getexecution to fetch failing test data, including screenshots and failure reasons. It can then draft a Slack alert or open a GitHub issue with the exact details. You don't have to dig through console logs yourself.

Build production-grade OpenAI Agents SDK workflows that trigger Mabl test plans and monitor execution data with strict safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Mabl (AI-Powered Test Automation) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate deployment gates using the Mabl MCP Server

Let your agent take charge of your release pipeline without human intervention. By exposing `mb.trigger_plan` to your agent, you can hook test execution directly into your deployment steps. The agent kicks off the test suite and monitors the run until it completes. Instead of polling manually, the agent uses `mb.get_execution` to track progress and flag failures. You get instant feedback in your CI pipeline, backed by the safety of OpenAI's built-in guardrails to prevent accidental triggers.

Inspect failures and analyze screenshots

When a test plan fails, your agent doesn't just report the error. It uses `mb.get_execution` to fetch the complete run details, including screenshots and failure analysis. This lets the agent pinpoint exactly which DOM element or API endpoint broke. This automated flow processes the test outcomes and hands off the diagnostic report to your engineering team, saving hours of manual triage.

Map environments and application targets

Keep your testing context accurate by letting your agent discover active targets dynamically. Using `mb.list_apps` and `mb.list_envs`, the agent maps out your staging and production endpoints. It combines this with `mb.list_labels` to target specific test suites based on the current deployment tag. This ensures your tests run against the correct environment without hardcoded configuration files.

Setup guide

Set up Mabl (AI-Powered Test Automation) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mabl (AI-Powered Test Automation) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mabl (AI-Powered Test Automation) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mabl (AI-Powered Test Automation) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mabl (AI-Powered Test Automation) Agent",
            instructions="You have access to Mabl (AI-Powered Test Automation) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and use the streamable HTTP transport class to connect. You will instantiate `MCPServerStreamableHttp` with the server URL and pass it into your agent constructor. Setting the cache option ensures fast tool discovery on startup.

Yes, you can. Your agent can query available runs with `mb.list_plans` and then execute them using `mb.trigger_plan`. This allows the agent to target specific environments and labels dynamically based on your deployment context.

The agent uses `mb.get_execution` to fetch failing test data, including screenshots and failure reasons. It can then draft a Slack alert or open a GitHub issue with the exact details. You don't have to dig through console logs yourself.

No, manual polling is unnecessary. Your agent can run an async loop that queries `mb.get_execution` at specified intervals, evaluating the status field automatically until the run completes.

Your Mabl API keys and test execution results are protected within the Vinkius V8 sandbox. No raw screenshots or sensitive environment variables are stored on our servers. All execution data transfers directly between your agent and the Mabl API.

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