MCP server · Developer tools
QAI Consultant MCP server
by gvasile29
Lets your AI answer QA questions using ISTQB, OWASP, ISO and EU AI Act standards, and score your test documents.
QAI Consultant is a helper for quality assurance work. It gives your AI assistant a set of QA standards and a few small calculators, so the answers you get are grounded in real testing knowledge instead of guesswork. It is handy if you write test plans, test strategies, or need to check how good an existing QA document is.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to something useful. This one connects your AI to a built-in library of QA standards and to a few small QA calculators. So when you ask a QA question, your AI can look things up in that library and run the numbers for you.
What this MCP server does
You ask your AI a QA question, for example about test strategy, risk, or effort. Your AI then uses this helper to search a local library of QA standards like ISTQB, OWASP, IEEE 829, ISO 26262, A-SPICE and the EU AI Act. The helper can also run small fixed calculations, like an effort estimate or a quality score for a test document. The results come back to your AI, which turns them into a normal answer for you. Nothing is sent to an outside service, and no API keys are needed.
Click to zoomWhat you can do with it
- Look up QA standards and methodologies to ground an answer
- List every document in the built-in QA knowledge base
- Estimate QA effort for a project using a fixed calculation
- Score an existing test plan, strategy or test case list from 0 to 100
- Analyze JUnit XML or CSV test results for flaky and slow tests
- Assess QA process maturity and EU AI Act readiness
Try asking your AI
- “What should a test strategy cover for a mobile banking app?”
- “Estimate the QA effort for a 6-month project with 4 testers.”
- “Review my test plan and tell me where it is weak.”
- “Look at these JUnit results and tell me which tests are flaky.”
What it gives back to you
You get answers in your chat, written by your own AI. Those answers can include lists of relevant standards, a quality score with findings, effort numbers, or a summary of test health. For document reviews and test results you also get short explanations and citations to the knowledge base. Everything shows up as normal text in the conversation.
Before you start
What you need
- The uv tool installed on your computer (a small free program that runs Python tools)
- An MCP client such as Claude Desktop or Claude Code
Good to know
The maturity level and EU AI Act readiness score are indicative only, not a certified audit, so do not treat them as official compliance results.
Install it with your AI
Add QAI Consultant MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check QAI Consultant MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
QA engineers, test leads and engineering managers who want their AI answers grounded in real testing standards.
