MCP server · Productivity

gut MCP server

Have your AI answer yes/no, pick-one, or rating questions about lots of text, fast and cheaply.

Productivity For customer support Data Science Tools

gut is a small helper that lets your AI make quick judgment calls about text, like deciding if something is spam or which team a ticket belongs to. It gives back a clear answer such as YES, NO, or UNSURE instead of a long paragraph you have to read. It is handy if you deal with lots of messages, tickets, or comments and want fast, simple decisions on each one.

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, in this case a connection to gut so it can make quick judgement calls on text. Once it is connected, you can ask your AI things like whether a comment looks like spam, and the helper does the actual deciding. You still talk to your AI like normal; the helper works behind the scenes.

What this MCP server does

You give your AI some text and a simple question, like is this spam or which team owns this. Your AI passes that to the gut helper. The helper runs a small model that answers with a probability or a choice, not a paragraph. Then your AI tells you the answer: yes, no, unsure, a category, or a rating. You can do this for one piece of text or for up to a thousand at once.

What you can do with it

Check if a comment or message looks like spam
Sort tickets into teams or categories
Rate how urgent something is on a scale like can wait, this week, right now
Flag when the answer is not clear and should go to a person
Run the same question across many files, commits, or search results in one go
Ask several judgment questions about one piece of text at the same time

Try asking your AI

“Is this comment spam? yes or no”
“Which team owns this ticket: billing, support, or engineering?”
“How urgent is this email: can wait, this week, or right now?”
“Go through these customer reviews and tell me which ones mention delivery problems”

What it gives back to you

You get a clear answer for each piece of text: YES, NO, or UNSURE, or a category like a team name, or a rating like this week. The reply also shows which model gave the answer and how confident it was. When you ask about many texts, you get a list of answers in the same order. There is no long paragraph to read, just the decision.

Before you start

What you need

Python installed on your computer if you want to run it locally
A TypeSafe API key if you use their Jev model (a kind of password for apps; the site gives you one)
An API key or a local model setup if you use another provider like OpenRouter, OpenAI, Ollama, or a CPU model

Good to know

It can make a wrong call, so for important or risky decisions use the unsure option and let a person check.

Install it with your AI

Add gut 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 gut 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 4,361 MCP servers here for you.