MCP server · Analytics

KeyNeg MCP server

Lets your AI read text and tell you how negative it is, plus pull out the main complaints.

Analytics For customer support For marketing For pr and communications Data Platforms

KeyNeg is a small helper that gives your AI a new skill: reading the mood of text, especially the negative side. You paste in a review, a support ticket, or a survey answer, and your AI comes back with labels like "poor customer service" and the words that stood out. It is handy if you deal with lots of customer messages, feedback, or comments and want a quick read on how upset people are.

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 KeyNeg, a sentiment analysis engine that runs on your own computer. So when you ask your AI to check how negative a piece of text is, it quietly asks KeyNeg, and KeyNeg sends back the answer.

What this MCP server does

You paste some text into your chat and ask your AI to look at the sentiment. Your AI passes that text to the KeyNeg helper running on your machine. KeyNeg reads the text and scores it against a long list of negative sentiment labels, like "rude" or "broken product". It sends the top labels and scores back to your AI, which shows them to you in the chat. Some features, like pulling out keywords or analyzing many texts at once, need a paid tier.

Flow diagram: you ask your AI “How negative is this customer review?”, on your own computer the KeyNeg MCP server works with your own computer, and you get back top complaints and scores.

Click to zoom

What you can do with it

Check how negative a customer review is
Pull out the top complaint labels from a support ticket
Extract the specific words and phrases that signal a problem
Get an overall read like strongly negative or mildly negative
Analyze a batch of texts in one go (paid tiers)
Look up the full list of sentiment labels the tool knows
Check which tier you are on and how many calls you have left

Try asking your AI

“Analyze the sentiment of this customer review: The service was terrible and the staff was rude.”
“What are the main complaints in these support tickets? Here they are: ...”
“Is this feedback positive or negative? Here is the text: ...”
“Extract the key issues from this employee survey response: ...”

What it gives back to you

You get back a short list of sentiment labels with scores, like "poor customer service" at 0.72, so you can see what the text leans toward. Some tools also return the keywords that stood out, and a full analysis adds an overall label like strongly negative. Everything shows up right in your chat as a small list or summary.

Before you start

What you need

Python installed on your computer
The KeyNeg sentiment engine (keyneg-enterprise-rs) installed from its own package index
The ONNX model files downloaded to a folder on your computer
A license key from grandnasser.com if you want keywords, batch analysis, or the full label list

Good to know

Keyword extraction and batch analysis need a paid license, and the free tier only gives you 3 sentiment labels and 100 calls per day.

Install it with your AI

Add KeyNeg 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 KeyNeg 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.