Can the AI provide the exact step where a test case failed?

Yes. If an execution failed, the agent uses `list_runs` for the instance. Since an instance maps directly to test steps, the AI inherently decodes the exact execution traces to show you the failing parameters.

Is PractiTest's requirement and issue tracing accessible to the AI?

Yes. Tools like `list_requirements` and `list_issues` expose full traceability trees. You can ask exactly how many QA instances are mapped to Requirement 5.

Do I need to copy the project ID separately?

Yes. In PractiTest, APIs execute cleanly isolated within specific Project instances. You must provide the numeric Project ID alongside your Personal Token so the underlying `pt-engine` binds queries strictly to that project.

PractiTest MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: PractiTest
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect PractiTest through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="PractiTest Assistant",
            instructions=(
                "You help users interact with PractiTest. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from PractiTest"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PractiTest MCP Server

Connect your PractiTest workspaces to any AI agent and empower it to orchestrate the entire QA lifecycle from physical requirements tracing to defect mapping natively via chat conversations.

The OpenAI Agents SDK auto-discovers all 10 tools from PractiTest through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries PractiTest, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Test Cases & Sets — Tell the AI to investigate any Test Case or Test Set, discovering exact preconditions and expected results (list_tests, get_test, list_sets)
Test Instances & Runs — Retrieve deep execution histories pinpointing exactly which step caused a regression bounding PASSED/FAILED statuses (list_runs)
Requirements Tracking — Audit physical system compliance extracting arrays dictating QA delivery thresholds (list_requirements)
Issue Mapping — Find exact Software Defects bound natively to QA traces verifying complex failure logic (list_issues)

The PractiTest MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PractiTest to OpenAI Agents SDK via MCP

Follow these steps to integrate the PractiTest MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from PractiTest

Why Use OpenAI Agents SDK with the PractiTest MCP Server

OpenAI Agents SDK provides unique advantages when paired with PractiTest through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

PractiTest + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the PractiTest MCP Server delivers measurable value.

Automated workflows: build agents that query PractiTest, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries PractiTest, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through PractiTest tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query PractiTest to resolve tickets, look up records, and update statuses without human intervention

PractiTest MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect PractiTest to OpenAI Agents SDK via MCP:

get_set

Get full details of a PractiTest test set including name, status, instances count, and execution summary

get_test

Get full details of a PractiTest test case including name, description, preconditions, steps, expected results, custom fields, and requirement links

list_custom_fields

List all custom fields in a PractiTest project. Returns field names, types, applicable entities, and possible values

list_instances

List all test instances in a PractiTest test set. Instances are test-set-specific copies of test cases. Returns instance IDs, test references, and last run statuses

list_issues

List all issues (defects) in a PractiTest project. Returns issue names, statuses, severities, and linked test references

list_requirements

List all requirements in a PractiTest project. Requirements provide traceability to test cases and defects. Returns names, statuses, and linked test counts

list_runs

List all runs for a PractiTest test instance. Runs record actual test execution results. Returns run IDs, statuses (PASSED/FAILED/BLOCKED/NOT_RUN/N_A), durations, and timestamps

list_sets

List all test sets in a PractiTest project. Test sets group test instances for execution. Returns set names, statuses, planned/actual dates, and assigned testers

list_tests

List all test cases in a PractiTest project. PractiTest is an end-to-end test management platform with traceability from requirements to defects. Returns test names, IDs, statuses, custom fields, and traceability links. Uses JSON:API format

list_users

List all users in the PractiTest account. Returns user names, emails, roles, and statuses

Example Prompts for PractiTest in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with PractiTest immediately.

"List all tests inside our active QA regression instance and find the ones mapped as failed."

"Do we have any new custom fields we should be aware of inside the requirements area?"

"Are there any open defects (issues) linked directly to testing scenarios surrounding multi-currency operations?"

Troubleshooting PractiTest MCP Server with OpenAI Agents SDK

Common issues when connecting PractiTest to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

PractiTest + OpenAI Agents SDK FAQ

Common questions about integrating PractiTest MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.