How to Use the Exact Online Bouw MCP in Vercel AI SDK

Q: How do I stream Exact Online Bouw ledger updates using the Vercel AI SDK?

Use the createcosttransaction tool within your streaming route. Pass the tool to streamText and let the Vercel AI SDK handle the real-time JSON generation. The client will stream the transaction status directly to your React components as it processes.

Q: What happens if a time entry fails during a live stream?

The SDK catches the error from createtimetransaction and streams the failure state to the UI. Your application can catch this error block on the client side to let the user correct the hours immediately.

Pipe real-time Dutch construction financial data directly into your React components using the Exact Online Bouw MCP Server and 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 Exact Online Bouw MCP to Vercel AI SDK

Create your Vinkius account to connect Exact Online Bouw 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 Exact Online Bouw with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream project creations to React

The `create_project` tool lets your Vercel AI SDK app spin up new Dutch construction jobs and instantly push the record straight to your Next.js UI. Instead of making users stare at a loading spinner, your app streams the new project ID and CRM account details directly to the browser. That means your site foremen see active jobs pop up on their dashboards the second they're created. It matches project variables against your Exact Online database behind the scenes, cutting out manual ERP data entry.

Stream time entries with the Vercel AI SDK

The `create_time_transaction` tool logs hours right from the job site and streams the updated budget status back to your frontend. Your Vercel AI SDK client handles the employee ID, dates, and hours, updating progress bars in real-time without refreshing the page. This live loop helps project managers spot labor overruns before they get out of hand. Running this MCP server alongside Vercel Edge Functions keeps your database connection fast and your UI responsive.

Render live financial budget alerts

The `list_project_hour_budgets` tool pulls current labor limits so your interface can flag overages before they hit the general ledger. By combining this with the Vercel AI SDK, your app streams live warning flags directly into the supervisor's active session. This approach stops bad entries before they cause Dutch G-account compliance issues. The UI updates dynamically as the model reads the hours, keeping your office and field aligned.

Setup guide

Set up Exact Online Bouw 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 Exact Online Bouw 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 Exact Online Bouw 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 Exact Online. 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 Exact Online Bouw 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 Exact Online Bouw MCP in Vercel AI SDK

Use the `create_cost_transaction` tool within your streaming route. Pass the tool to `streamText` and let the Vercel AI SDK handle the real-time JSON generation. The client will stream the transaction status directly to your React components as it processes.

Yes. The server connects via a standard HTTP transport, allowing your Vercel AI SDK application to query project data from Edge runtimes. You just initialize the client with `createMCPClient` using the Vinkius endpoint.

Vinkius handles the OAuth2 handshake for you behind a single access token. You pass this token in the headers when calling `createMCPClient` in your Vercel AI SDK setup, keeping your client credentials secure.

The SDK catches the error from `create_time_transaction` and streams the failure state to the UI. Your application can catch this error block on the client side to let the user correct the hours immediately.

All project budgets, subcontractor hours, and cost transactions remain encrypted in transit. The MCP server runs in an isolated sandbox, meaning your division IDs and employee records are never exposed or stored outside the active session.

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