How to Use the Knoema MCP in Vercel AI SDK

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

Use createMCPClient with the HTTP transport URL. Call mcpClient.tools() and pass them to your streamText function. Always call mcpClient.close() when the stream finishes.

Q: What is the best way to find specific Knoema indicators using the Vercel AI SDK?

Pass the searchdataseries tool to your agent. It will query the exact indicators across all datasets and stream the matches back to your user.

Stream global economic indicators directly into your Next.js frontend with this Knoema integration for the 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 Knoema MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Dataset Discovery Live via MCP Server

The `search_datasets` tool lets your agent find exact economic sources while the user watches the UI update in real time. Instead of showing a spinner while your backend hunts for global statistics, this MCP Server streams the search results straight into a React component. Once the user clicks a dataset, your client fires off `get_dataset_metadata`. This pulls the required variables and dimensions, letting you instantly render a dynamic filter panel without waiting for a full page reload.

Render Time-Series Charts Instantly

The `get_data_series` tool extracts specific macroeconomic data points using a dataset ID and mnemonics. Your edge function calls this server and pipes the raw numbers directly into your charting library as they arrive. You do not need to build complex polling logic. When you need the absolute newest figures, `get_latest_dataset_data` grabs the most recent data points, pushing updates to your Svelte or Vue frontend the second the agent finishes the fetch.

Map Regional Statistics Automatically

The `list_dataset_regions` tool returns every geographic boundary supported by a specific Knoema dataset. Your application uses this to populate dropdown menus on the fly, ensuring users only select regions that actually have data. You pair this with `list_data_frequencies` and `list_data_units` to format the incoming stream. If the data is annual GDP in USD, your UI knows exactly how to format the axis labels before the first data point even hits the browser.

Setup guide

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

Use `createMCPClient` with the HTTP transport URL. Call `mcpClient.tools()` and pass them to your `streamText` function. Always call `mcpClient.close()` when the stream finishes.

Yes, that is the primary use case. The client streams the output of `get_data_series` directly into your UI components as the agent processes the numbers.

It works natively on the edge. You just need to configure the HTTP transport to talk to the Vercel AI SDK client.

Pass the `search_data_series` tool to your agent. It will query the exact indicators across all datasets and stream the matches back to your user.

The MCP Server only touches macroeconomic time-series data and global statistics. Vercel AI SDK routes these requests through your configured endpoint token, meaning no raw economic data persists in the edge function after the stream 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