How to Use the Fiscal Data (U.S. Treasury) MCP in Vercel AI SDK

Q: How do I set up the Fiscal Data (U.S. Treasury) MCP server with Vercel AI SDK?

Install @ai-sdk/mcp and ai via npm. Initialize the client using createMCPClient with the Vinkius HTTP transport URL, then pass mcpClient.tools() directly to streamText. Remember to call mcpClient.close() once the execution completes to prevent memory leaks in your Edge Functions.

Q: Can I stream real-time exchange rates using Fiscal Data (U.S. Treasury) on Vercel AI SDK?

Yes, you can. The getratesofexchange tool pulls the latest Treasury reporting rates and streams them directly into your UI components. Your AI client processes the raw numbers instantly, meaning your users see current currency conversions without waiting for a full page reload.

Q: How does the Fiscal Data (U.S. Treasury) MCP server handle complex queries in Vercel AI SDK?

Your AI client uses the querydataset tool to request specific endpoints from the 170 available federal datasets. The SDK handles the incoming JSON payload, allowing the LLM to format and stream the filtered tables directly into your application's UI.

Feed live U.S. Treasury data directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fiscal Data (U.S. Treasury) MCP to Vercel AI SDK

Create your Vinkius account to connect Fiscal Data (U.S. Treasury) 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 Fiscal Data (U.S. Treasury) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Treasury rates in Vercel AI SDK

The `get_rates_of_exchange` tool feeds official government exchange rates directly into your frontend application. Your AI client grabs the latest figures and streams them to the user's screen in real time, bypassing slow API gateways or stale local databases. You build the interface using Next.js or React, and the data renders as it arrives. No spinners, no stale caches, just raw Treasury figures popping up instantly on the page.

Query 170+ federal datasets instantly

The `query_dataset` tool opens up the entire U.S. Treasury API database directly to your LLM. Your agent specifies the exact endpoint path, like the accounting or public debt tables, and filters the raw JSON payload before it hits your edge functions. Because the Vercel AI SDK handles the payload directly in the streaming loop, your interface displays the filtered financial records immediately. You get clean, structured data directly from the official source without writing custom backend routing.

Direct access to Monthly Treasury Statements

The `get_mts_table_1` tool delivers the latest Monthly Treasury Statement receipts and outlays directly to your application. Your AI client parses these tables to build on-the-fly financial charts and projections for your users. You combine this tool with `get_mts_table_9` to analyze the federal budget trust funds. This MCP server lets your application run on Vercel Edge Functions, keeping execution times under the limit by processing the raw numbers right at the network edge.

Setup guide

Set up Fiscal Data (U.S. Treasury) 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 Fiscal Data (U.S. Treasury) 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 Fiscal Data (U.S. Treasury) 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 Fiscal Data (U.S. Treasury). 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 Fiscal Data (U.S. Treasury) 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 Fiscal Data (U.S. Treasury) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai` via npm. Initialize the client using `createMCPClient` with the Vinkius HTTP transport URL, then pass `mcpClient.tools()` directly to `streamText`. Remember to call `mcpClient.close()` once the execution completes to prevent memory leaks in your Edge Functions.

Yes, you can. The `get_rates_of_exchange` tool pulls the latest Treasury reporting rates and streams them directly into your UI components. Your AI client processes the raw numbers instantly, meaning your users see current currency conversions without waiting for a full page reload.

Your AI client uses the `query_dataset` tool to request specific endpoints from the 170 available federal datasets. The SDK handles the incoming JSON payload, allowing the LLM to format and stream the filtered tables directly into your application's UI.

Yes, the integration runs perfectly on Edge Functions. Because the MCP server handles the heavy lifting of connecting to the federal endpoints, your edge function remains lightweight and executes within the standard platform limits.

The MCP server acts as a secure, zero-trust bridge that only transmits public U.S. Treasury fiscal data, monthly statements, and exchange rates. No private application database keys or user secrets are ever exposed to the public API, and Vinkius runs the connector in an isolated, ephemeral sandbox.

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