Complete AI Training

MCP server · Developer tools

Unfour MCP server

by zyqzyq

Let your AI check API responses, server logs, and database state to help you trace backend bugs.

Flow diagram: you ask your AI “Why is the login endpoint failing?”, on your own computer the Unfour MCP server works with unfour, and you get back answers in your chat.

Unfour is a desktop app for backend developers who need to chase down a bug across an API, a server, and a database. It keeps your API requests, SSH sessions, and database queries in one place, and it includes an optional MCP server so your AI assistant can work with those same connections. It is handy if you spend your day debugging live systems and want your AI to help look things up instead of just chatting.

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 an app or service. This one connects your AI to Unfour, so it can use the API, SSH, and database connections you already saved there. When you ask a question, the AI goes through Unfour to look things up or run a check, then tells you what it found.

What this MCP server does

You ask your AI something about a running backend, like why an endpoint is failing. The AI uses this helper to reach the saved connections inside Unfour. Unfour then sends the API request, reads server logs over SSH, or runs a database query for you. The results come back through the AI, so you see the evidence in your chat. Risky actions still need your confirmation, and everything stays in your local workspace.

Flow diagram: you ask your AI “Why is the login endpoint failing?”, on your own computer the Unfour MCP server works with unfour, and you get back answers in your chat. Click to zoom

What you can do with it

  • Send a saved API request and show you the response
  • Read server logs over an SSH connection you set up
  • Run a database query and return the rows
  • Check database state to confirm a fix worked
  • Start or cancel a local Flow runbook and show its history
  • Re-check an endpoint after a change

Try asking your AI

  • “Send the saved request for the login endpoint and show me the response status and body”
  • “Check the last 50 lines of the app log on the staging server for errors around 2pm”
  • “Run this query on the orders database and tell me how many rows have a null customer id”
  • “Start the checkout Flow runbook and show me the step results”

What it gives back to you

You get back answers in plain chat: response statuses and bodies, log lines, query results, and step outcomes from a runbook. It can also show you the history of a Flow run. If it made a change, it tells you what it changed. Everything appears as text in your conversation, not as files you have to open.

Before you start

What you need

  • The Unfour desktop app installed and running
  • Saved API, SSH, or database connections inside Unfour
  • Codex or Cursor set up to use the Unfour MCP server

Good to know

It can run real API requests, SSH commands, and database queries, and some actions can change or delete data, so keep the confirmation prompts on.

Install it with your AI

Add Unfour 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 Unfour 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.

Sign in Become a member

Who it's for

Backend developers and anyone who debugs APIs, servers, and databases as part of their daily work.