How to Use the EOD Historical Data MCP in Vercel AI SDK

Q: How do I handle API rate limits when using EOD Historical Data with the Vercel AI SDK?

You track your usage via getuser to monitor remaining API credits directly within your edge functions. If you hit limits, you can implement edge-side caching or use Redis to store the EOD historical JSON responses before they reach your React components.

Q: Can I stream technical indicator charts using EOD Historical Data and Vercel AI SDK?

Yes, you feed gettechnicalindicators to the SDK's streamText function to generate real-time charts. The AI client processes the raw indicator arrays and streams the formatted data points directly into your charting library on the client side.

Q: How do I set up the EOD Historical Data MCP Server in a Next.js edge route?

You initialize the connection using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Then, you pass the tools directly to your Vercel AI SDK streamText call and ensure you run mcpClient.close() to prevent memory leaks in your serverless environment.

Q: How does the SDK handle bulk exchange queries?

You call getbulkfundamentals to fetch data for an entire exchange, which the SDK streams in chunks. This prevents your Edge Functions from timing out when handling massive financial datasets.

Stream live financial data and historical stock charts directly into your Next.js frontend with 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 EOD Historical Data MCP to Vercel AI SDK

Create your Vinkius account to connect EOD Historical Data 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 EOD Historical Data with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live market prices using Vercel AI SDK

The `get_real_time` tool feeds live OHLCV pricing directly into your Next.js frontend without lag. Your users see stock price ticks update instantly in the UI as the model streams its response, bypassing the standard loading spinner pattern. By combining this with `get_technical_indicators`, your AI client renders live, annotated financial charts using this MCP server. You pass these tools directly into `streamText` to build responsive, interactive trading interfaces that run in lightweight edge functions.

Render deep company fundamentals on the fly

The `get_fundamentals` tool pulls complete balance sheets, income statements, and valuation metrics for any supported global ticker. The Vercel AI SDK streams these structured data blocks straight into custom React components as the model processes them. If you need to display sector-wide comparisons, `get_bulk_fundamentals` fetches entire exchange datasets in one go. This lets your web application build dynamic, side-by-side comparison tables that render progressively while the user reads the analysis.

Build live-updating financial calendars via MCP Server

The `get_calendar_earnings` tool queries upcoming corporate earnings events to populate interactive timeline components. Using the MCP Server, your Next.js application feeds these schedules directly to the user's viewport without full-page reloads. You can combine this with `get_calendar_dividends` and `get_calendar_splits` to build a unified corporate events feed. The Vercel AI SDK handles the asynchronous streaming of these timelines, letting your agents generate personalized portfolio alerts on the edge.

Setup guide

Set up EOD Historical Data 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 EOD Historical Data 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 EOD Historical Data 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 EOD Historical Data. 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 EOD Historical Data 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 EOD Historical Data MCP in Vercel AI SDK

You track your usage via `get_user` to monitor remaining API credits directly within your edge functions. If you hit limits, you can implement edge-side caching or use Redis to store the EOD historical JSON responses before they reach your React components.

Yes, you feed `get_technical_indicators` to the SDK's `streamText` function to generate real-time charts. The AI client processes the raw indicator arrays and streams the formatted data points directly into your charting library on the client side.

You initialize the connection using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Then, you pass the tools directly to your Vercel AI SDK `streamText` call and ensure you run `mcpClient.close()` to prevent memory leaks in your serverless environment.

You call `get_bulk_fundamentals` to fetch data for an entire exchange, which the SDK streams in chunks. This prevents your Edge Functions from timing out when handling massive financial datasets.

No, the MCP server processes ticker symbols, CUSIP mapping requests via `get_id_mapping`, and fundamental data queries in memory without logging your proprietary financial inputs. All market data requests pass through a zero-trust V8 sandbox on Vinkius before reaching your application.

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