How to Use the Outlier Detection Engine MCP in Claude Code

Run headless anomaly detection with Claude Code and the Outlier Detection Engine for reliable, scriptable data validation.

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 Code

Create your Vinkius account to connect Outlier Detection Engine to Claude Code — 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Headless statistical execution

The `detect_outliers` tool functions perfectly in your CI/CD pipelines or terminal scripts. You get deterministic anomaly detection without any graphical overhead. Claude Code connects to the engine via the CLI, allowing you to pipe your data directly into the analysis. It is built for backend tasks where speed and reliability are the only metrics that matter.

Scriptable anomaly detection

You can automate your data cleaning by calling the Outlier Detection Engine from your shell. It reads your datasets and outputs the findings in a format your scripts can parse immediately. Claude Code manages the tool connection, so your pipeline stays clean. It is a straightforward way to enforce statistical standards in your production builds.

Deterministic data pipeline integration

By using the `detect_outliers` tool, your pipelines avoid the instability of probabilistic models. It uses standard Z-Score and IQR calculations to ensure your data stays within expectations. Claude Code handles the tool invocation as part of your automated workflow. You define the threshold, and the engine executes the logic immediately.

Setup guide

Set up Outlier Detection Engine MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see outlier-detection-engine-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Outlier Detection Engine transactions." It will automatically discover and invoke the available Outlier Detection Engine tools.

Terminal

claude mcp add --transport http outlier-detection-engine-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Outlier Detection Engine MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "outlier-detection-engine-mcp": {
      "type": "url",
      "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.