How to Use the ContextQA MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK agent automatically fix broken tests using ContextQA?

Yes. Your agent uses getexecution to inspect AI-healing run states and pinpoint exactly where a test broke. Armed with this data, the agent can modify the test configuration or update your application code to resolve the mismatch.

Q: How does the agent handle complex, multi-step test suites?

The agent uses listsuites to inspect the structure of your GUI tests, then coordinates execution using triggerrun. It tracks the progress of each step by querying the run status directly.

Run self-healing test suites directly from your OpenAI Agents SDK pipelines with zero-config tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ContextQA MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control ContextQA environments inside OpenAI Agents SDK

`list_environments` and `list_projects` give your OpenAI agents direct visibility into your test target layers and project UUIDs. Your agent reads these configurations to map out execution spaces before triggering any code changes. Instead of hardcoding environment variables, you pass this MCP Server to your agent constructor. The agent dynamically targets the correct staging or production environment based on the real-time system state.

Trigger and track self-healing test runs

`trigger_run` launches live testing jobs against your pipelines while `get_execution` monitors the exact AI-healing states. Your agent watches these runs, catching failures as they happen without manual polling. If a test fails, the agent uses `list_executions` to inspect the internal interaction logs and isolate the broken element. It then decides whether to patch the codebase or update the test suite.

Audit API and GUI test structures

`list_api_tests` extracts your native REST and OpenAPI configurations, and `list_suites` pulls down your asynchronous GUI test payloads. Your agent maps these test cases directly to your endpoints to find gaps in coverage. Using `list_cases` and `get_case`, the agent validates data science object extraction boundaries. It matches actual test case definitions against expected behaviors to keep your QA suite accurate.

Setup guide

Set up ContextQA 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 ContextQA tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents and instantiate the MCPServerStreamableHttp client with the Vinkius endpoint URL. Pass this server object in the mcp_servers list when initializing your Agent. The SDK automatically registers all ten tools for your agent to use.

Yes. Your agent uses `get_execution` to inspect AI-healing run states and pinpoint exactly where a test broke. Armed with this data, the agent can modify the test configuration or update your application code to resolve the mismatch.

You can easily define runtime checks in your SDK configuration to inspect parameters before your agent calls `trigger_run`. This stops your agent from launching runaway test suites or targeting wrong environments.

The agent uses `list_suites` to inspect the structure of your GUI tests, then coordinates execution using `trigger_run`. It tracks the progress of each step by querying the run status directly.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your API tokens and raw test payloads never persist on our servers. All traffic is ephemeral and encrypted, so your proprietary API structures and test results stay private.

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