How to Use the EOD Historical Data MCP in OpenAI Agents SDK

Q: How do I connect the EOD Historical Data MCP to the OpenAI Agents SDK?

You'll pip install openai-agents, then create an MCPServerStreamableHttp instance with your Vinkius endpoint URL. Pass that server object to your Agent constructor in the mcpservers list. The agent discovers all 26 tools automatically.

Q: Can my agent with the OpenAI Agents SDK filter stocks using EOD Historical Data?

Yes, that's a perfect use case. Your agent can use the getscreener tool to find stocks based on fundamental or technical metrics. You can ask it to "find US stocks with a market cap over $100B and a dividend yield above 3%."

Q: Can I use this to find insider trades?

You can. The server includes the getinsidertransactions tool. Your agent can pull Form 4 filings for any ticker, giving you a direct feed of trades made by company executives.

Build production financial agents with the OpenAI Agents SDK, backed by real-time market data from EOD Historical Data.

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 OpenAI Agents SDK

Create your Vinkius account to connect EOD Historical Data to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Backtest Strategies with Real Data

Use the `get_eod_historical` and `get_intraday_historical` tools to pull clean price data directly into your agent. Your OpenAI agent automatically discovers these tools, letting you ask for things like "get the last 5 years of daily prices for AAPL" without writing API-specific code. The SDK's guardrails validate the agent's plan before it ever calls the EOD Historical Data API. This setup helps you build safer, more predictable financial bots. You can also pull `get_splits` and `get_dividends` to make sure your backtests are adjusted correctly. The full request and response trace shows up right in your OpenAI dashboard, so you know exactly what data your agent used for its analysis.

Run Fundamental Analysis with an MCP Server

This MCP Server exposes tools like `get_fundamentals` and `get_bulk_fundamentals` for deep company analysis. Your agent can pull income statements, balance sheets, and cash flow data for a single stock or an entire exchange. Just ask it to "compare the P/E ratios for tech stocks on the NASDAQ." Because the OpenAI Agents SDK lets you create specialized agents, you can build a team of them. Have one agent for fundamental analysis and another for technicals using `get_technical_indicators`. The SDK handles the handoff between them, so each agent does one job well.

Monitor Live Markets & News Feeds

Connect your agent to market data using the `get_real_time` tool for delayed quotes. It can also monitor financial news with `get_news` and analyze the underlying tone with the `get_sentiments` tool. Since the tools are auto-discovered, you can build agents that react to market events. For example, an agent could fetch breaking news, check the sentiment, and then pull the latest intraday price. This all happens as part of a single, validated action plan.

Setup guide

Set up EOD Historical Data MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all EOD Historical Data tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives EOD Historical Data tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate EOD Historical Data tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="EOD Historical Data Agent",
            instructions="You have access to EOD Historical Data tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You'll `pip install openai-agents`, then create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL. Pass that server object to your `Agent` constructor in the `mcp_servers` list. The agent discovers all 26 tools automatically.

Yes, that's a perfect use case. Your agent can use the `get_screener` tool to find stocks based on fundamental or technical metrics. You can ask it to "find US stocks with a market cap over $100B and a dividend yield above 3%."

The SDK itself doesn't manage external API rate limits. Your agent's calls to this MCP server count against your EOD Historical Data account's API limits. You can check your current usage with the `get_user` tool.

You can. The server includes the `get_insider_transactions` tool. Your agent can pull Form 4 filings for any ticker, giving you a direct feed of trades made by company executives.

Your requests for financial data—like stock prices or fundamentals—are sent through Vinkius's ephemeral, zero-trust sandbox. The connection is secured end-to-end, and Vinkius doesn't log the financial data payloads, only the operational metrics of the MCP call.

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