How do I securely obtain my Qase Token?

Log in to Qase.io and click your profile icon to go to **Account settings**. Select **API Tokens** (or sometimes found under Apps for an integration token), and click **Create a new API token**. Add a name, click generate, and copy the string provided. It takes exactly 15 seconds. Paste it here to authenticate. Your token is encrypted at rest and injected securely at runtime.

Can my AI write test scripts using the case details?

Absolutely. Inside your IDE (like Cursor), you can ask the agent to 'Fetch case #12 from Qase project PROJ'. The tool retrieves the precise steps, preconditions, and expected results. The agent can then automatically generate Playwright, Cypress, or Selenium scripts based exactly on those Qase definitions.

How can I check the results of a recent QA cycle?

Ask your agent to `list_runs` for your project. This will surface your recent executions. If you notice a run with a high failure rate, ask the agent to pull `get_run` with that run's ID to dive into specifics and see which modules failed the automated checks.

Can it help me track Jira bugs linked to tests?

Yes. By using the `list_defects` capability, your AI can pull all registered defects in a Qase project. If your Qase is integrated with Jira or GitHub, the returned defect data includes external issue links, helping developers immediately map a failed test to the corresponding engineering ticket.

Qase MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Qase
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Qase through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

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

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Qase "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Qase?"
    )
    print(result.data)

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 Qase MCP Server

Connect your Qase workspace to any AI agent and integrate test management deeply into your development workflow.

Pydantic AI validates every Qase tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Overviews — Retrieve all active projects, view health metrics, and get total counts of test cases, runs, and defects instantly
Test Cases & Suites — Explore your test hierarchy, pull specific test steps, and check case automation statuses without opening the Qase dashboard
Test Runs & Execution — List all test runs, monitor execution status (passed, failed, blocked), and dive deep into test run analytics
Defects & Milestones — Track project milestones and extract all logged defects linked to failed test cases, complete with severity levels and issue links

The Qase MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI 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 Qase to Pydantic AI via MCP

Follow these steps to integrate the Qase MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Qase with type-safe schemas

Why Use Pydantic AI with the Qase MCP Server

Pydantic AI provides unique advantages when paired with Qase through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Qase integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Qase connection logic from agent behavior for testable, maintainable code

Qase + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Qase MCP Server delivers measurable value.

Type-safe data pipelines: query Qase with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Qase tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Qase and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Qase responses and write comprehensive agent tests

Qase MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Qase to Pydantic AI via MCP:

get_case

Retrieves details for a specific test case

get_project

Retrieves details for a specific project

get_run

Retrieves details for a specific test run

list_cases

Lists test cases in a project

list_defects

Lists all defects linked to test case failures

list_milestones

Lists all milestones in a project

list_plans

Lists all test plans in a project

list_projects

Lists all projects in Qase

list_runs

Lists all test runs in a project

list_suites

Lists test suites in a project

Example Prompts for Qase in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Qase immediately.

"List all Qase projects and show me their overall health."

"Fetch the details of test case ID 45 in the WEB project."

"Are there any recent defects added for the WEB project?"

Troubleshooting Qase MCP Server with Pydantic AI

Common issues when connecting Qase to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Qase + Pydantic AI FAQ

Common questions about integrating Qase MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Qase MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.