How to Use the Outlier Detection Engine MCP in Cursor

Q: How do I add the Outlier Detection Engine MCP Server to Cursor?

Add the server configuration to your .cursor/mcp.json file in your project root. Cursor will detect the server and let your agent call the detectoutliers tool during active coding sessions.

Let Cursor write code using real, mathematically proven anomalies found in your active workspace 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 Cursor

Create your Vinkius account to connect Outlier Detection Engine to Cursor — 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Feed real statistical anomalies into your Cursor code

Integrating this MCP Server gives your workspace the `detect_outliers` tool so Cursor can find bad data points and write code to handle them. Your agent gets exact statistical indices instead of writing code based on blind guesses. This means you can ask Cursor to write a cleanup script for a specific messy JSON file, and it will use the actual math from the tool to target the correct rows.

Debug data pipelines using this statistical engine

This MCP Server runs the `detect_outliers` tool directly inside Cursor's Agent mode to run checks on your test datasets. When your data pipeline throws an error, the agent runs the tool to see if a skewed value broke the system. You get immediate feedback right in your editor sidebar without opening a separate Jupyter notebook. It speeds up debugging because you see the exact mathematical reason a test failed.

Analyze local database exports inside your editor

Scanning workspace exports with the `detect_outliers` tool works directly on your local files using deterministic IQR or Z-Score algorithms. Cursor reads the generated list of anomalies to help you refactor your data schemas. You don't have to guess if your database has bad entries. The tool gives Cursor the precise coordinates of every outlier, making it easy to write targeted migration scripts.

Setup guide

Set up Outlier Detection Engine MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Outlier Detection Engine MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Outlier Detection Engine transactions." If the MCP tools are loaded correctly, Cursor will call the Outlier Detection Engine tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Add the server configuration to your `.cursor/mcp.json` file in your project root. Cursor will detect the server and let your agent call the `detect_outliers` tool during active coding sessions.

Yes, your agent can run the tool to find the exact anomalies, then write a Python or SQL script to clean those specific rows.

Yes, this MCP Server runs as a local background process connected to your editor. Cursor communicates with the server to analyze your files without sending your code or data to external APIs.

Yes, you tell the agent which statistical method to apply. Cursor then passes that parameter to the tool, ensuring the math matches your pipeline's requirements.

The server runs in a secure sandbox on your machine. Your numeric JSON files are parsed locally, ensuring your proprietary data points never upload to any third-party model servers.

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