How to Use the DataScope MCP in Vercel AI SDK

Q: How do I handle DataScope authentication in Vercel AI SDK?

You configure OAuth using the authProvider option when setting up createMCPClient. This keeps your API keys secure on Vercel's edge network while letting users fetch their own form submissions.

Q: Can Vercel AI SDK stream PDF links from DataScope?

Yes, by combining streamText with the getsubmissionpdfurl tool. The AI client writes the markdown link in real-time as soon as the MCP Server returns the download URL.

Q: How do I clean up DataScope MCP connections in Vercel AI SDK?

Always invoke mcpClient.close() inside your API route or edge function once the stream finishes. This prevents your serverless environment from hitting connection limits on the form metadata endpoints.

Q: Can I filter forms by user ID?

Yes, you can pass a user ID to listformsubmissions to narrow down the results. This lets your agent display only the relevant field answers for a specific inspector.

Stream DataScope field inspection data directly into your React components 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 DataScope MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live stream DataScope form submissions to your UI

The `list_form_submissions` tool pulls raw answers directly from your field forms so your Vercel AI SDK client can render them live. Instead of making users wait for a full API response, this MCP Server lets you pipe incoming inspection records straight to the browser. You configure the transport using `createMCPClient` and pass the tools directly to `streamText`. Your frontend displays the field answers chunk by chunk as they arrive, keeping your Next.js UI highly responsive.

Generate PDF URLs on the edge with Vercel AI SDK

The `get_submission_pdf_url` tool retrieves the exact download link for any completed field audit. This means your Vercel AI SDK agent can immediately hand a PDF download link to a user during a chat session. By deploying this to Vercel Edge Functions, you keep latency low. Just make sure to call `mcpClient.close()` after fetching the PDF URL to prevent dangling connections.

Map offline team locations inside React

The `list_tracked_locations` tool reads coordinate histories from field agents who collected data offline to expose them to your MCP client. Your Vercel AI SDK app can feed these coordinates directly into interactive map components. This setup lets your agent analyze geographical gaps while streaming the visual updates. You can manage access tokens safely on the server side using the built-in OAuth support.

Setup guide

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

You configure OAuth using the `authProvider` option when setting up `createMCPClient`. This keeps your API keys secure on Vercel's edge network while letting users fetch their own form submissions.

Yes, by combining `streamText` with the `get_submission_pdf_url` tool. The AI client writes the markdown link in real-time as soon as the MCP Server returns the download URL.

Always invoke `mcpClient.close()` inside your API route or edge function once the stream finishes. This prevents your serverless environment from hitting connection limits on the form metadata endpoints.

Yes, you can pass a user ID to `list_form_submissions` to narrow down the results. This lets your agent display only the relevant field answers for a specific inspector.

Your mobile form submissions and tracked GPS coordinates are processed entirely in memory within the Vercel V8 sandbox. No field audit data is stored on Vinkius, and transport-level encryption secures the pipeline from the mobile device to your React frontend.

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