How to Use the Autodesk Construction Cloud MCP in Vercel AI SDK

Q: How do I connect Vercel AI SDK to Autodesk Construction Cloud?

Run npm install ai @ai-sdk/mcp. Initialize your connection using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the resulting tools directly to streamText.

Build live construction dashboards by streaming Autodesk Construction Cloud data directly to your frontend 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 Autodesk Construction Cloud MCP to Vercel AI SDK

Create your Vinkius account to connect Autodesk Construction Cloud 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 Autodesk Construction Cloud with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Hub and Project Data Live

The `list_hubs` and `list_projects` tools pull core architectural directories straight into your React components. Your Vercel AI SDK client fetches the raw folder structures and streams them directly into the DOM. Users watch the UI populate as `get_project_details` resolves the metadata. You skip the loading states entirely while the MCP Server handles the background API requests.

Vercel AI SDK Issue Tracking

Calling `list_issues` grabs the active punch list items and feeds them to your UI in real-time. End users see the site problems appear on screen immediately instead of waiting for a slow batch payload to finish. When someone spots a new defect on the floor plan, the client fires `create_issue` to log it. The `get_issue_details` tool then fetches the exact confirmation data to update the local state instantly.

Render Asset Directories Instantly

The `list_top_folders` and `list_folder_contents` tools expose the blueprint and spec directories. Your application streams these file trees straight to the browser using Edge Functions. Clicking a specific piece of equipment triggers `list_assets` and `get_asset_details`. The specific HVAC or structural steel data renders live as the chunks arrive over the wire.

Setup guide

Set up Autodesk Construction Cloud 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 Autodesk Construction Cloud 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 Autodesk Construction Cloud 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 Autodesk. 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 Autodesk Construction Cloud 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 Autodesk Construction Cloud MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp`. Initialize your connection using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the resulting tools directly to `streamText`.

Yes, the server provides tools for that exact task. You call `list_top_folders` to get the root structure. Then you pass those IDs to `list_folder_contents` to navigate deeper into the project files.

Vinkius hosts the server externally via HTTP. Your Vercel Edge Functions just make standard fetch requests to the endpoint token. This keeps your edge deployment lightweight.

You do not write auth logic. Vinkius manages the complex OAuth flow and provides a single endpoint token. Your frontend passes that token in the transport configuration.

Vinkius runs every request inside an ephemeral V8 Isolate Sandbox. Your site plans, punch lists, and asset details remain strictly isolated. The container dies immediately after the HTTP response closes.

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