How to Use the Magicplan MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Magicplan?

Run npm install @ai-sdk/mcp. Set up createMCPClient with your Vinkius HTTP transport URL. Pass the tools directly to streamText to start rendering project data.

Q: Can the Vercel AI SDK stream Magicplan measurements live?

Yes. When the agent calls getplanmeasurements, the Vercel AI SDK streams the numeric data straight to your React frontend. The user sees the square footage numbers populate instantly.

Q: How do I manage workspace users with Magicplan and Vercel AI SDK?

You call listworkspaceusers through the active MCP connection. The SDK streams the active team roster back to your client. You then render those names into an assignment dropdown.

Build live real estate dashboards. Stream Magicplan spatial data directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magicplan MCP to Vercel AI SDK

Create your Vinkius account to connect Magicplan 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 Magicplan with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Spatial Data to the UI

The `get_project_floor_plan` tool pulls raw spatial layouts from Magicplan. Your Vercel AI SDK frontend catches this data as it streams in. Instead of forcing users to stare at a spinner while the server builds a massive JSON object, the UI renders room dimensions and wall segments instantly. You pair this with `get_plan_measurements` to populate live tables in Next.js. As the AI reads the numeric measurements, the client components update. The user watches the project scope build itself right on their screen.

Magicplan MCP Server Form Integration

The `list_available_forms` tool fetches your data collection checklists straight from the workspace. You map these directly into React components. When a contractor needs specific site data, the AI client pulls the exact requirements without a manual database sync. Then you hit `get_plan_form_data` to read the submitted answers. Because this runs through an active MCP connection, the AI evaluates the form completeness live. It immediately prompts the user for missing safety checklist items before they leave the job site.

Render Live Project Estimates

The `list_project_estimates` tool grabs the high-level financial quotes attached to a floor plan. You feed this into a streaming text response. The client sees the total project cost appear piece by piece. For the granular breakdown, the AI calls `get_estimate_details`. It extracts line-item costs for materials and labor. You bind these results to a dynamic chart in Svelte, letting the end user watch their renovation budget calculate itself in real time.

Setup guide

Set up Magicplan 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 Magicplan 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 Magicplan 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 Magicplan. 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 Magicplan 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 Magicplan MCP in Vercel AI SDK

Run `npm install @ai-sdk/mcp`. Set up `createMCPClient` with your Vinkius HTTP transport URL. Pass the tools directly to `streamText` to start rendering project data.

Yes. When the agent calls `get_plan_measurements`, the Vercel AI SDK streams the numeric data straight to your React frontend. The user sees the square footage numbers populate instantly.

You call `list_workspace_users` through the active MCP connection. The SDK streams the active team roster back to your client. You then render those names into an assignment dropdown.

No. Vinkius handles the authentication layer. You just pass your single Vinkius endpoint token into the transport configuration and close the client when the session ends.

Your raw floor plan coordinates and financial line-items stay secure. The Vinkius V8 Isolate Sandbox executes the request in an ephemeral, zero-trust environment. The server destroys the instance the millisecond the API responds.

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