Skip to content
Vinkius

ml-kmeans Connector for AI agents.

1 live capability

Group complex datasets into distinct clusters for customer segmentation and spatial routing.

Live agent request ml-kmeans / Connector

Waiting for input…

AI Agent

Why people use ml-kmeans

K-Means Cluster Engine for Precise Data Segmentation

This Connector replaces the guesswork with a dedicated math engine. You feed it the raw numbers, and it handles the heavy lifting of finding the centroids and assigning every point to a cluster. You get a clean, structured output that stays the same every time you run it.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • Visual Studio Code
  • Windsurf

What Vinkius changes

You get mathematically consistent data segmentation without the unpredictability of LLM guessing.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

  1. Real-world use case 01

    Customer Tiering

    A marketing lead wants to group 5,000 customers into 4 tiers based on monthly spend and login frequency to target ads better.

  2. Real-world use case 02

    Traffic Anomaly Detection

    A security analyst needs to separate normal web traffic from malicious patterns by clustering IP behavior data to find outliers.

  3. Real-world use case 03

    Logistics Hub Planning

    A logistics company wants to take 200 delivery points and find the 5 best central hub locations for their fleet.

Complete set · 1capability

The complete ml-kmeans capability set.

These are the exact actions your AI can choose when you ask it to work with ml-kmeans.

Capability set01 / 01

01

1 capability in this set.

Part of 1 available through ml-kmeans.

  1. 01 Capability

    Calculate kmeans

    Run a deterministic K-Means clustering on any numerical dataset to find optimal groups. It returns the centroids and the group assignments for every point in your data.

Set up in minutes

One URL. Then ask ml-kmeans to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use ml-kmeans from the conversation.

Choose your client

Live preview
Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP
https://edge.vinkius.com/vk_preview_6Ww4kVrA1RFFv9i4y5sPargfFbR4nVocQXy4cCBt/mcp
  1. Step 01

    Open Connectors

    In Claude Web or Claude Desktop, open Settings and choose Connectors.

  2. Step 02

    Add the URL

    Choose Add custom connector, name it ml-kmeans, and paste the URL above.

  3. Step 03

    Turn it on in chat

    Select +, open Connectors, and enable ml-kmeans for the conversation.

Where the request belongs

Work ml-kmeans can move forward.

Built around the request

This is for data professionals and operations leads who need hard numbers. It's for the person tired of 'fuzzy' AI results and looking for deterministic math to organize large datasets.

01

Data Analyst

They use this to group 10,000+ rows of sales data into tiers for reporting without manual filtering.

02

Ops Engineer

They use it to separate normal network traffic from malicious spikes using hard mathematical clustering.

03

Logistics Manager

They use it to group delivery stops into geographic zones to determine optimal hub locations for a fleet.

04

Marketing Researcher

They use it to create hard customer personas based on spending and behavior data instead of guessing.

Build the capability set

Add more capabilities.

Each Connector adds new actions and data without changing how you work.

Browse Connectors
Silhouette Score Engine logo
01 1 capability

Silhouette Score Engine

Evaluate the quality and cohesion of clustering algorithms (like K-Means) with mathematically perfect Silhouette scores computed local.

View Connector
Nyckel ML logo
02 10 capabilities

Nyckel ML

Classify data and perform semantic search via Nyckel. track ML functions, samples, and labels directly from your AI agent.

View Connector
PCA Dimensionality Engine logo
03 1 capability

PCA Dimensionality Engine

Perform native Principal Component Analysis to safely reduce high-dimensional datasets without losing critical variance.

View Connector
Distance Metrics Engine logo
04 1 capability

Distance Metrics Engine

Calculate mathematically perfect Cosine, Euclidean, Manhattan, and Chebyshev distances between high-dimensional vectors local. Essential for embedding comparisons.

View Connector
SMOTE Oversampling Engine logo
05 1 capability

SMOTE Oversampling Engine

Balance skewed datasets instantly by generating mathematically sound synthetic minority data points via KNN.

View Connector
Embedding Similarity Calculator logo
06 Managed Connector

Embedding Similarity Calculator

Calculate mathematical distances and similarity scores between multidimensional numerical vectors.

View Connector

Bring your own AI

Change the model, client or framework. Keep ml-kmeans connected.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • VS Code
  • Windsurf
  • ZCode
  • Cline
  • Zed
  • Continue
  • Kiro
  • Roo Code
  • Zencoder
  • Goose
  • Void
  • Augment Code
  • Amp
  • Qodo
  • Tabnine
  • Pieces
  • Sourcegraph Cody
  • JetBrains
  • Warp
  • Amazon Q
  • Antigravity
  • BoltAI
  • Raycast
  • Jan
  • LM Studio
  • AnythingLLM
  • Open WebUI
  • Msty
  • Cherry Studio
  • LibreChat
  • TypingMind
  • Chorus
  • 5ire
  • n8n
  • LangChain
  • LlamaIndex
  • CrewAI
  • Vercel AI SDK

Before you connect

Questions about ml-kmeans.

The practical details behind the request, access and result.

Can the K-Means Cluster Engine handle my customer data?

Yes, it is perfect for grouping customers based on numerical factors like spending, frequency, or age. It turns raw data into organized tiers.

Is the K-Means Cluster Engine accurate?

It is much more accurate than a standard AI guess because it uses a deterministic math algorithm. The results will be consistent every time you run them.

Can I use K-Means Cluster Engine for maps?

Yes, it can group coordinates into geographic zones. This helps you find the best central hub locations for delivery routes or retail coverage.

Does it work for large datasets?

Yes, it is designed for high-speed local execution, making it ideal for processing large lists of data points quickly.

What is a centroid in this context?

A centroid is the mathematical center point of a cluster. The engine calculates these to help you identify the 'heart' of each data group.

Will the results change if I run the same data twice?

No, because the math is deterministic. Unlike a standard LLM, this engine will give you the exact same clusters every time you provide the same data.

Is the clustering process fully deterministic?

Yes, it guarantees consistent, mathematically precise assignments for every execution, completely avoiding LLM hallucination.

What kind of distance metric is used?

The engine leverages standard Euclidean distance measurement, making it highly effective for uniform, continuous numeric datasets.

How fast is the data processing?

Native execution within the Vinkius Edge runtime ensures that thousands of rows are fully clustered in mere milliseconds.

One connection away

Give your agent a direct line to ml-kmeans.

Connect ml-kmeans once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available