How to Use the Applitools MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK agent delete test batches in Applitools?

Yes, the agent can call deletebatch if you grant it permission. Make sure to use the SDK's built-in guardrails to prevent accidental deletions of your visual test history.

Q: How does OpenAI Agents SDK handle Applitools API key validation?

Your agent runs validatekey during startup to verify connectivity. If the key is invalid, the SDK tracing dashboard flags the error immediately before running any visual tests.

Q: Can my agent filter Applitools baselines by branch?

Your agent calls listbranchbaselines to isolate visual states for specific feature branches. This keeps your main visual branch clean while the OpenAI agent validates experimental UI changes.

Manage Applitools visual test runs and baselines directly within your OpenAI Agents SDK workflow.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Applitools MCP to OpenAI Agents SDK

Create your Vinkius account to connect Applitools 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 Applitools with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit test runs with OpenAI Agents SDK

Let your OpenAI agent dig into test results without leaving the terminal. By calling `list_batches` and `get_batch_stats`, the agent checks whether your latest UI changes broke anything in Eyes. The SDK's built-in guardrails ensure the agent doesn't run wild. It checks the visual diff status safely, only proceeding with deployment steps once the Applitools batch passes.

Clean up outdated Applitools baselines

Redesigned pages make old visual baselines useless. Your agent uses `list_baselines` to find stale visual layouts and targets them for removal using `delete_baseline`. Tracing in the OpenAI dashboard shows you exactly which baseline ID was wiped. You get a clean visual history without manual cleanup work in the Eyes dashboard.

Deep-dive session debugging via MCP Server

When a test batch fails, your agent needs details fast. It invokes `get_session` to pull the exact visual differences and failures within a specific Applitools batch. This MCP Server integration lets your OpenAI agent decide if a visual change is a real bug or an expected update. It handles the triage so your developers don't have to.

Setup guide

Set up Applitools 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 Applitools tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Applitools tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Applitools 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="Applitools Agent",
            instructions="You have access to Applitools 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 Applitools. 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 Applitools 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 Applitools MCP in OpenAI Agents SDK

Install the Python SDK and configure the Applitools MCP Server streamable HTTP transport. Pass the server URL to your Agent constructor so it can automatically discover the visual testing tools.

Yes, the agent can call `delete_batch` if you grant it permission. Make sure to use the SDK's built-in guardrails to prevent accidental deletions of your visual test history.

Your agent runs `validate_key` during startup to verify connectivity. If the key is invalid, the SDK tracing dashboard flags the error immediately before running any visual tests.

Your agent calls `list_branch_baselines` to isolate visual states for specific feature branches. This keeps your main visual branch clean while the OpenAI agent validates experimental UI changes.

Your Applitools API keys and visual test baselines never pass through OpenAI's servers. The Applitools MCP Server acts as a secure bridge, meaning your visual regression data is processed locally and securely.

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