How to Use the Outlier Detection Engine MCP in Vercel AI SDK

Stream real-time statistical anomalies into your UI with the Outlier Detection Engine for AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Outlier Detection Engine to Vercel AI SDK — 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Deterministic anomaly detection in your UI

Stop guessing which data points matter. The `detect_outliers` tool calculates Z-Scores or IQR bounds instantly, letting your AI SDK application flag problematic records as they stream. Your users won't stare at loading spinners. Since this MCP Server runs locally, results push directly into your React or Next.js components for immediate feedback.

Client-side data validation

Handle CSV and JSON payloads without sending sensitive information to an external API. The engine keeps processing local to your edge function environment. Your application logic stays clean and predictable. You get the raw numeric results back from `detect_outliers` and decide exactly how to render them.

Real-time outlier visualization

Connect this MCP Server to your frontend to build live monitoring dashboards. The tool outputs specific outlier indices that you can map to charts or tables. Accuracy matters when you are building user-facing products. By using deterministic math instead of LLM hallucinations, your interface displays facts, not guesses.

Setup guide

Set up Outlier Detection Engine MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Outlier Detection Engine tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Outlier Detection Engine transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the MCP client package via npm. Initialize the connection using your Vinkius endpoint and pass the tools directly into your `streamText` function.

Yes. Since the server returns structured JSON, your AI SDK agents parse the outlier results as standard tool calls. You just map the output to your UI state.

It does. The server architecture supports HTTP transports, making it compatible with serverless environments. Just ensure your environment has enough memory for your specific dataset size.

Your data never leaves your local environment. This server processes numeric CSV and JSON records entirely on your machine before the AI SDK ever sees the final summary.

The tool returns an empty list. Your code should handle this as a standard success state, confirming the dataset passed your statistical checks.

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