• OUTLIERS
  • CLUSTERS
  • CENTROIDS
  • HUMAN

How to detect data anomalies with your AI

Connect the Distance Metrics Engine to your AI client. It uses spatial math to find the points that sit too far from the rest of your data.

Ask AI about this page

Short answer

How can I find outliers in my data using AI?

Your AI calculates the distance between individual data points and their nearest cluster centroids. This identifies points that fall outside normal ranges, giving you a clear list of anomalies to investigate.

Results

Where your anomalies land.

The AI processes your raw numbers and sorts the results into these categories.

OUTLIERS

Detected anomalies

The AI flags points that sit far from the cluster center. You get a list of specific coordinates or values that look suspicious.

CLUSTERS

Grouped data points

The AI organizes your data into logical groups. This shows you the normal density of your dataset.

CENTROIDS

Center point locations

The AI identifies the mathematical middle of your data groups. These serve as the baseline for what constitutes a normal value.

HUMAN

Manual review needed

The AI can't decide if an outlier is a mistake or a breakthrough. You decide if the flagged data requires a fix or further study.

The workflow

What your AI does when the data arrives.

The AI handles the heavy math so you don't have to write custom scripts for every dataset.

  1. Map the data

    The AI looks at your dataset to understand the distribution of your points.

    calculate_distance

  2. Find the centers

    The AI determines where the middle of each data cluster sits.

    calculate_distance

  3. Measure deviations

    The AI runs distance checks on every point against those centers.

    calculate_distance

  4. Flag the outliers

    The AI isolates the points with the highest distance scores for your review.

    calculate_distance

Try it

Copy these to start.

Use these prompts to trigger the detection process.

Starting points

Replace the bracketed text with your specific file names or data sources.

Distance Metrics Engine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_y2uLWGNkX2DGyvuukg2OciAQezxFmCM92SNAHYKa/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Distance Metrics Engine capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "distance-metrics-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_y2uLWGNkX2DGyvuukg2OciAQezxFmCM92SNAHYKa/mcp"
    }
  }
}
Copy into chat04

  • Find all outliers in my sales_data.csv file.

  • Calculate the distance from the cluster centers for the sensor_logs dataset.

  • Identify any data points in the user_activity_log that are far from the main group.

  • Check the customer_metrics sheet for anomalies using distance metrics.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Distance Metrics Engine once, then ask.

Just click the link to connect. Your credentials stay encrypted, and you can immediately start asking your AI to run these calculations.

Connect Distance Metrics Engine to your AI

FAQ

How this task behaves.

  • 01

    Can the AI automatically delete outliers?

    No. The AI only identifies and flags the points. You must manually remove or edit data in your original source.

  • 02

    Does the AI change my original data files?

    No. The AI reads your data to perform calculations, but it does not write back to or modify your files.

  • 03

    What kind of data can it process?

    It works with any numerical datasets where distance between points can be measured.

  • 04

    Can the AI explain why a point is an outlier?

    Yes. Since it uses distance from the centroid, it can tell you exactly how far a point sits from the average.

  • 05

    Does it work with real-time data streams?

    The AI processes the data you provide in the chat or via the connected file.

  • More questions about Distance Metrics Engine? The Connector page answers them. See everything the Distance Metrics Engine Connector can do

Connect Distance Metrics Engine to Claude, Cursor, ChatGPT & more