How to Use the Geometry Calculator MCP in Vercel AI SDK

Q: How do I feed the Geometry Calculator tools into Vercel AI SDK streamText?

You import the MCP client, call mcpClient.tools(), and pass those tools directly into the helper. Your agent will automatically decide when to invoke calculate2darea or calculatedistance based on the user prompt. Remember to call mcpClient.close() when the stream finishes.

Give your Vercel AI SDK frontend the power to stream instant Euclidean distance and volume calculations directly to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geometry Calculator MCP to Vercel AI SDK

Create your Vinkius account to connect Geometry Calculator 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 Geometry Calculator with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream local spatial math directly to Vercel AI SDK

This MCP Server streams real-time spatial calculations directly to your Vercel AI SDK interface. Your Next.js interface needs to show physical dimensions instantly without waiting for slow API roundtrips. By hooking this engine into your edge runtime, your agent queries `calculate_2d_area` and streams the exact dimensions straight to the browser. Users watch the math happen in real time instead of staring at a blank loading state. Setting this up takes seconds. You install the packages, initialize the client, and feed `calculate_distance` directly into the streamText function. The engine processes everything locally in Vinkius, meaning your serverless functions don't get bogged down with heavy math.

Zero-latency spatial calculations on the edge

The Geometry Calculator MCP Server runs local spatial math in a dedicated V8 sandbox to keep your edge functions lightweight. Heavy geometry calculations usually kill performance in serverless environments. This tool moves the heavy lifting of `calculate_3d_volume` to a dedicated host. Your edge functions stay lightweight, fast, and cheap to run. The architecture ensures that your client gets immediate geometric answers. You don't have to spin up a separate Python math microservice. Just call the tool from your TypeScript code, get the result, and close the connection.

Secure coordinate processing without databases

This local geometry engine processes sensitive coordinate maps in an ephemeral sandbox without external API calls. Stop sending physical dimensions to third-party endpoints. This server runs in a zero-trust environment, processing geometric inputs and returning raw numbers. Your Vercel AI SDK setup keeps complete control over the data flow. Once the calculation completes, the session wipes itself clean. No logs are kept, and no spatial data is stored.

Setup guide

Set up Geometry Calculator 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 Geometry Calculator 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 Geometry Calculator 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 geometry-calculator. 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 Geometry Calculator 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 Geometry Calculator MCP in Vercel AI SDK

You import the MCP client, call `mcpClient.tools()`, and pass those tools directly into the helper. Your agent will automatically decide when to invoke `calculate_2d_area` or `calculate_distance` based on the user prompt. Remember to call `mcpClient.close()` when the stream finishes.

Yes, this setup is fully compatible with Edge runtimes. Because Vinkius hosts the actual math engine, your edge code only needs to handle lightweight HTTP requests. It keeps your bundle size small and execution times under the edge limit.

The server runs inside a dedicated V8 isolate sandbox that scales instantly. When your frontend user drags a slider to recalculate a 3D volume, the agent triggers `calculate_3d_volume` repeatedly. The local engine handles these rapid calculations without throttle limits.

No, this MCP Server handles all parsing internally. When your agent identifies a shape, it sends the raw parameters to `calculate_2d_area` or `calculate_3d_volume`. The tool returns clean JSON, which the SDK streams directly into your UI.

We never store your raw coordinates or radius values. Every geometric request is processed in an ephemeral sandbox that is destroyed immediately after execution. Your spatial parameters never touch a persistent disk.

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