How to Use the Haversine Distance Engine MCP in Vercel AI SDK

Q: How do I connect the Haversine Distance Engine to the Vercel AI SDK?

Install @ai-sdk/mcp. Initialize the client with createMCPClient using your endpoint URL. Then extract the tools and pass them to streamText.

Build real-time location features into your Next.js apps with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Haversine Distance Engine MCP to Vercel AI SDK

Create your Vinkius account to connect Haversine Distance Engine to Vercel AI SDK 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 Haversine Distance Engine with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Distance Data to the UI

The `calculate_distance` tool lets your Vercel AI SDK agent instantly process GPS coordinates. You pass in two sets of latitude and longitude points. The engine runs the math and returns exact distances in both kilometers and miles. Users hate waiting for map APIs to load. Because this MCP server runs fast, the calculated distance streams right into your React frontend without a loading spinner. Your end users see the exact mileage pop up the second the agent finishes thinking.

Edge-Ready Vercel AI SDK Routing

Calling `calculate_distance` works perfectly from Edge Functions. Setting up the MCP client requires `createMCPClient` with an HTTP transport. The agent decides when it needs to know how far apart two places are. That means you don't write custom routing logic. You just provide the tools. The AI grabs the coordinates, hits the engine, and feeds the resulting distance straight into the `streamText` response.

Build Location-Aware Chatbots

Exposing `calculate_distance` to your chatbot gives it spatial awareness. If a user asks how far the nearest warehouse is, the agent knows exactly how to get that number. It calls the tool, does the math, and replies instantly. You handle the frontend while the MCP standard handles the connection. Pass the tool list into your generation call, and let the agent do the heavy lifting. Just remember to call `mcpClient.close()` when the session ends.

Setup guide

Set up Haversine Distance 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 Haversine Distance 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 Haversine Distance 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 Haversine Engine. 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 Haversine Distance 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 Haversine Distance Engine MCP in Vercel AI SDK

Install `@ai-sdk/mcp`. Initialize the client with `createMCPClient` using your endpoint URL. Then extract the tools and pass them to `streamText`.

Yes. The engine returns both miles and kilometers by default. Your AI agent can pick which unit to display to the user.

It does. The tool execution happens on the backend, and the resulting text streams directly into your Next.js UI. Users see the output in real time.

The tool rejects them. It enforces strict boundaries for latitude and longitude. The agent receives the error and can ask the user for correct inputs.

It calculates the math in memory and drops the data immediately. The server never stores the latitude or longitude pairs you send. Your location data remains completely ephemeral.

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