How to Use the K-Means Cluster Engine MCP in Mastra AI

Q: How can my Mastra AI agent use the K-Means Cluster Engine to segment users?

Your agent calls the calculatekmeans tool with a list of user data points. Then, you can use Mastra AI's workflow engine to route the logic based on the clusterId returned for each user.

Q: Can I make a Mastra AI agent ask for approval before running calculatekmeans with the K-Means Cluster Engine?

Yes. You can configure requireToolApproval in your Mastra AI agent. This creates a human-in-the-loop step where the workflow will pause until someone manually approves the calculatekmeans operation.

Q: How do I pass a large dataset to calculatekmeans from my agent?

You pass the data as a JSON array in the points parameter. The server is designed to handle thousands of data points efficiently, so for most use cases, you can send the data directly.

Q: What about the privacy of my user data with this clustering server?

This server only processes the dataset of points you provide. It's a sandboxed function that can't see anything else about your workflow or system. The data is discarded from memory the moment the clusters are returned.

Add deterministic data clustering to your Mastra AI workflows for reliable, automated segmentation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect K-Means Cluster Engine MCP to Mastra AI

Create your Vinkius account to connect K-Means Cluster Engine to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup K-Means Cluster Engine with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branch Workflows on Cluster ID

The `calculate_kmeans` tool takes a set of data points and assigns each one to a numbered cluster. You get back your original data, but with a new `clusterId` property on each point. In a Mastra AI workflow, you use this output for conditional logic. If a user lands in cluster 2, trigger an alert. If they're in cluster 5, add them to a marketing campaign. It makes your segmentation pipelines automatic and predictable.

A Resilient Clustering Step

This MCP Server just does one thing: K-Means clustering. It's a managed Vinkius service, so you don't have to worry about the underlying math, dependencies, or infrastructure. Mastra AI's built-in retries mean that if a network blip happens during the call to `calculate_kmeans`, your workflow won't die. It just tries again. This keeps your segmentation pipeline running without manual intervention.

Typed Inputs for Your Agent

When you connect Mastra AI to this MCP Server, the `calculate_kmeans` tool's schema is automatically understood. Your agent knows exactly what to pass: an array of points and an integer for 'k'. This prevents a whole class of runtime errors. Your TypeScript-native agent gets the right data structure every time, so you can build complex chains of operations with confidence that the data contracts will be honored.

Setup guide

Set up K-Means Cluster Engine MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All K-Means Cluster Engine tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "k-means-cluster-engine-mcp-client",
  servers: {
    "k-means-cluster-engine-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "K-Means Cluster Engine Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to K-Means Cluster Engine tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent K-Means Cluster Engine transactions"
);
console.log(result.text);

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 ml-kmeans. 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 K-Means Cluster 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 K-Means Cluster Engine MCP in Mastra AI

Your agent calls the `calculate_kmeans` tool with a list of user data points. Then, you can use Mastra AI's workflow engine to route the logic based on the `clusterId` returned for each user.

Mastra AI's engine will automatically retry the call based on your configured policy. This makes your workflow resilient to transient network issues without you writing any retry logic.

Yes. You can configure `requireToolApproval` in your Mastra AI agent. This creates a human-in-the-loop step where the workflow will pause until someone manually approves the `calculate_kmeans` operation.

You pass the data as a JSON array in the `points` parameter. The server is designed to handle thousands of data points efficiently, so for most use cases, you can send the data directly.

This server only processes the `dataset` of points you provide. It's a sandboxed function that can't see anything else about your workflow or system. The data is discarded from memory the moment the clusters are returned.

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