How to Use the Twelve Data MCP in Pydantic AI

Q: Can I use Twelve Data for crypto pairs with Pydantic AI?

Yes. You call getcryptolist first, and then the resulting data—whether a list or a price point—is guaranteed to pass through validation, making it safe for your application.

Q: What financial data does Twelve Data provide for Pydantic AI?

The server handles stock quotes, forex rates (getexchangerate), and historical OHLCV candle data. Every piece of this pricing information is treated as a strongly typed object.

Q: What if I need currency conversion using Twelve Data with Pydantic AI?

The convertcurrency tool handles the exchange, and because you're using Pydantic, you don't have to worry about data structure mismatch. The output is clean.

Q: Does Twelve Data support listing available forex pairs for Pydantic AI?

Yep. Use getforexlist to get the list, and then use gettimeseries to fetch historical data. The structured output makes chaining these calls very predictable.

Type-safe financial agents with Pydantic AI. Guaranteed structured output from Twelve Data MCP Server calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Twelve Data MCP to Pydantic AI

Create your Vinkius account to connect Twelve 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 Twelve Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Real-Time Pricing Data

To get a quote, call `get_quote`. Since you're using the Pydantic framework, the response data is guaranteed to match your defined schema—no unexpected fields. This keeps your agent reliable. Need live prices quickly? Use `get_real_time_price`. The output remains strictly typed, meaning if the API changes, your agent fails loud and clear instead of silently corrupting.

Analyze Market Trends

Run technical indicators like the Stochastic Oscillator using `get_stochastic`. Pydantic validation ensures that the resulting overbought/oversold values are correctly typed for your downstream logic. For trend analysis, call `get_macd`. The structured nature of this output means you can rely on the data points being exactly where they should be in your Python model.

Search and List Instruments

Searching for symbols happens via `search_symbols`, which filters by type and exchange. The tool's response is validated, so you know the exact structure of every instrument returned. Listing stocks with `get_stock_list` works the same way—the resulting list adheres to your model definition, making consumption safe for your agent.

Setup guide

Set up Twelve 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": {
        "twelve-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Twelve 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 Twelve 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 Twelve 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 Twelve Data MCP in Pydantic AI

You wrap the MCP Server toolset and pass it as an input to your Agent. The framework intercepts every response, validating it against Pydantic models before passing it to your code.

Yes. You call `get_crypto_list` first, and then the resulting data—whether a list or a price point—is guaranteed to pass through validation, making it safe for your application.

The server handles stock quotes, forex rates (`get_exchange_rate`), and historical OHLCV candle data. Every piece of this pricing information is treated as a strongly typed object.

The `convert_currency` tool handles the exchange, and because you're using Pydantic, you don't have to worry about data structure mismatch. The output is clean.

Yep. Use `get_forex_list` to get the list, and then use `get_time_series` to fetch historical data. The structured output makes chaining these calls very predictable.

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