How to Use the Outlier Detection Engine MCP in Claude

Q: How do I configure the Outlier Detection Engine inside Claude Desktop?

Open your claudedesktopconfig.json file and add the server to your mcpServers list. Once you restart Claude Desktop, the agent will automatically call the tool whenever you ask it to analyze datasets.

Stop letting Claude Desktop guess which data points are anomalies by running deterministic statistical tests on your local files.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outlier Detection Engine MCP to Claude Desktop

Create your Vinkius account to connect Outlier Detection Engine to Claude Desktop — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Outlier Detection Engine with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run deterministic mathematical tests on local files

The `detect_outliers` tool acts as a local MCP Server to give Claude Desktop the math it needs to find anomalies without guessing. Instead of letting your agent eyeball a CSV and hallucinate outliers, this tool executes exact Z-Score or IQR algorithms on your local dataset. You get back precise row indices and values that violate your statistical boundaries. Since it runs as a local subprocess on your machine, you can process massive data files right from your chat input.

Spot data errors directly from the Claude Desktop chat

This MCP Server exposes the `detect_outliers` tool to analyze your local files in seconds. When you ask your agent to check a database export, it calls the tool to flag the exact rows that skew your metrics. You don't have to write custom Python scripts or load heavy libraries. Claude Desktop uses the local stdio transport to parse the results, letting you isolate bad data points immediately.

Clean up messy CSVs without leaving your workspace

Running the `detect_outliers` tool processes your local tabular data using clean, standard formulas. Your agent reads the output to understand exactly which points are statistical noise before you build your reports. This keeps your context window clean because you only pass the flagged anomalies back to Claude Desktop. You avoid dumping thousands of rows of raw data into the prompt just to find a few bad inputs.

Setup guide

Set up Outlier Detection Engine MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Outlier Detection Engine MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Outlier Detection Engine MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under outlier-detection-engine-mcp.

json

{
  "mcpServers": {
    "outlier-detection-engine-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by simple-statistics. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Outlier Detection Engine now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Outlier Detection Engine MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the server to your `mcpServers` list. Once you restart Claude Desktop, the agent will automatically call the tool whenever you ask it to analyze datasets.

Yes, it processes massive local files directly on your machine. Because this MCP Server runs locally via stdio, Claude Desktop doesn't need to upload your heavy datasets to a remote cloud.

Yes, you can tell your agent to use either method depending on your data distribution. Claude Desktop passes your choice directly to the statistical engine to execute the exact formula you want.

The tool ignores non-numeric and null values to prevent calculation errors. Claude Desktop will receive a clean list of actual outliers based strictly on the remaining valid numbers.

Your raw numeric datasets and CSV files stay entirely on your local machine during the calculation. This MCP Server processes the data locally, sending only the specific flagged outlier coordinates to Claude Desktop.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript