MCP server · API

qa-probe MCP server

Lets your AI read your QA results and explain in plain words why a page is blank or broken.

API Developer tools For it and development Delivery

qa-probe is a tool that checks your web app's backend routes and tells you why something is not working, for example why a page loads but shows no data. This MCP server is the part that lets your AI assistant read those results and explain them to you in normal language. It is handy if you work with a development team and keep hearing "the dashboard is empty again" without knowing why.

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 another tool. This one connects your AI to qa-probe, so the AI can look at your QA reports and answer questions about them. You ask in plain English, and the AI fetches the answer from qa-probe instead of guessing.

What this MCP server does

You ask your AI something like why a certain page shows no data. The AI passes that question to this helper, which reads the qa-probe results already saved on your computer. qa-probe has already checked each backend route and worked out a likely reason for each problem, such as an empty database or a feature flag being switched off. The helper sends back the reason, the evidence behind it, and how confident the tool is. Your AI then explains it to you in the chat, in everyday words.

Flow diagram: you ask your AI “Why is my orders page blank?”, on your own computer the qa-probe MCP server works with your QA results, and you get back A plain reason in your chat.

Click to zoom

What you can do with it

Ask why a specific page or route is showing no data
List all broken or degraded routes with their scores
Check whether an endpoint is returning data right now
See which backend routes a given page depends on
Find out which pages break if one endpoint goes down
Get a suggested fix for a problem like a disabled feature flag
Mark a finding as expected or as a real bug

What it gives back to you

You get answers in the chat, not files. The AI can give you a list of routes with their scores and status, a one line reason for a failure, or a suggested fix. Each answer comes with the evidence behind it and a confidence level, so you can tell a confirmed problem from a guess. If something could not be verified, the AI is told to say so instead of presenting it as a pass.

Before you start

What you need

Node.js installed on your computer
The qa-probe tool run at least once, so there are results to read
An AI assistant that supports MCP, such as Claude Code or Cursor

Good to know

It reads your QA reports and can probe your live backend endpoints, so only point it at systems you are allowed to test, and keep real passwords in environment variables rather than in the config file.

Install it with your AI

Add qa-probe 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 qa-probe 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.