How to Use the EOD Historical Data MCP in Pydantic AI

Q: How does Pydantic AI connect to the EOD Historical Data MCP server?

It's straightforward. Install pydantic-ai-slimmcp, then create an MCPToolset with your Vinkius URL. You pass that instance into the toolsets argument of your Agent.

Q: Can I use Pydantic AI and EOD Historical Data to get technical indicators?

Yes. When your agent uses the gettechnicalindicators tool, Pydantic AI validates the response. You'll get a clean object with correctly typed fields for indicators like RSI, SMA, or Bollinger Bands, ready for your code to use.

Q: Is it possible to search for assets with Pydantic AI and EOD Historical Data?

Definitely. The searchassets tool lets your agent find stocks or ETFs. The results are automatically validated, so you can reliably pipe the output—like a ticker symbol—into another tool call like getfundamentals.

Q: How do I get a list of all supported tickers for an exchange?

Your agent would use the getexchangesymbollist tool. It takes an exchange code, like 'US', and returns a validated list of all available symbols. This is useful for setting up bulk data operations.

Get type-safe, validated financial data in your Python app with Pydantic AI and 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 Pydantic AI

Create your Vinkius account to connect EOD Historical Data to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Structurally Valid Market Data

This MCP Server exposes 26 financial data tools, and Pydantic AI ensures every response is trustworthy. When your agent calls `get_fundamentals`, the JSON response is automatically parsed and validated against a Pydantic model. If a field is missing or has the wrong type, your code gets an immediate `ValidationError`. No more silent data corruption or defensive coding against inconsistent API responses. You can trust that the data from `get_eod_historical` has the `open`, `high`, `low`, and `close` fields you expect, every single time. It's correctness by default.

Build Reliable Financial Tools

Pydantic AI's focus on data integrity makes it a good fit for building tools where accuracy is non-negotiable. Use the `get_dividends` and `get_splits` tools to build a portfolio tracker, knowing the data structure is guaranteed to be correct. This approach makes your agent's logic simpler and more robust. Instead of writing `try/except` blocks to handle malformed data from the `get_real_time` tool, you just work with the validated Pydantic object. If the data is bad, the tool call fails before your code even sees it.

Mix and Match LLMs with this MCP Server

Pydantic AI is model-agnostic, so you can point it at OpenAI, Anthropic, Gemini, or a local model. The `MCPToolset` works the same way regardless of the backend LLM, which lets you choose the right model for your specific financial task. Your agent can use `get_screener` to filter assets with one model, then switch to another for nuanced analysis with `get_news` and `get_sentiments`. The core logic stays clean because Pydantic AI handles the tool-use abstraction layer.

Setup guide

Set up EOD Historical Data MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "eod-historical-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to EOD Historical Data tools.",
)

result = await agent.run("List recent EOD Historical Data transactions")
print(result.output)

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 Pydantic AI

It's straightforward. Install `pydantic-ai-slim[mcp]`, then create an `MCPToolset` with your Vinkius URL. You pass that instance into the `toolsets` argument of your `Agent`.

Yes. When your agent uses the `get_technical_indicators` tool, Pydantic AI validates the response. You'll get a clean object with correctly typed fields for indicators like RSI, SMA, or Bollinger Bands, ready for your code to use.

Definitely. The `search_assets` tool lets your agent find stocks or ETFs. The results are automatically validated, so you can reliably pipe the output—like a ticker symbol—into another tool call like `get_fundamentals`.

Your agent would use the `get_exchange_symbol_list` tool. It takes an exchange code, like 'US', and returns a validated list of all available symbols. This is useful for setting up bulk data operations.

Pydantic AI communicates with the MCP server over a secure HTTPS connection. The server itself, managed by Vinkius, runs your request for things like insider transactions or sentiment data in a sandboxed V8 isolate. This environment is single-use and its memory is wiped clean after your request is fulfilled.

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