How to Use the Upstream Lens MCP in Vercel AI SDK

Q: How do I handle complex filtering when listing projects with Upstream Lens and Vercel AI SDK?

You use the listprojectnotes tool. When calling it, you pass specific filters for the update date. The streamed results will only show notes matching your criteria.

Q: What is the data privacy handling when using Upstream Lens and Vercel AI SDK?

This MCP Server touches organizational metadata via getorganizationinfo. When implementing this with your agent, you must ensure that the client's credentials are secured during the OAuth flow.

Q: Does Upstream Lens support batch data checks using Vercel AI SDK?

You can check the API health first by calling checkapihealth. After confirming the connection is good, you'll stream the required data from tools like listportfolios.

Q: If I need to list all available portfolios using Upstream Lens and Vercel AI SDK, how do I structure the call?

You simply invoke the listportfolios tool. The resulting array of data will be streamed back through your agent's response handler for immediate UI display.

Show your users real-time data streams from Upstream Lens directly in their browser using 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 Upstream Lens MCP to Vercel AI SDK

Create your Vinkius account to connect Upstream Lens 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 Upstream Lens with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Operational Data Display

The `list_projects` tool lets you fetch a list of all environmental projects. You can stream this data to the UI, showing users which sites are currently active as they query it. Check on current operational status by using `list_portfolios`. The streamed results allow your frontend to update instantly without requiring the user to hit refresh.

Project Analysis and History

Need deep dive info? You can retrieve specific details about a property feature with `get_property_details`. This is perfect for displaying contextual data alongside AI responses. History matters. Call `list_project_notes` to pull records, letting the user filter these notes based on their update date as it appears in real-time.

Infrastructure Metadata Retrieval

The MCP Server provides basic organizational context via `get_organization_info`. This lets your agent know which client is making the request before showing results. You also get property data using `list_property_imagery`, providing a list of available imagery layers for any given location.

Setup guide

Set up Upstream Lens 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 Upstream Lens 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 Upstream Lens 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 Upstream Lens. 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 Upstream Lens 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 Upstream Lens MCP in Vercel AI SDK

You use the `list_project_notes` tool. When calling it, you pass specific filters for the update date. The streamed results will only show notes matching your criteria.

Yes. Because the Vercel AI SDK supports streaming, you can process streams coming from different tools, like running `list_projects` followed by querying `get_property_details`, and displaying both sequentially.

This MCP Server touches organizational metadata via `get_organization_info`. When implementing this with your agent, you must ensure that the client's credentials are secured during the OAuth flow.

You can check the API health first by calling `check_api_health`. After confirming the connection is good, you'll stream the required data from tools like `list_portfolios`.

You simply invoke the `list_portfolios` tool. The resulting array of data will be streamed back through your agent's response handler for immediate UI display.

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