How to Use the Kraken MCP in Pydantic AI

Q: How do I use the Kraken MCP server with Pydantic AI?

Install pydantic-ai-slimmcp and instantiate MCPToolset("http://...") with your Vinkius server URL. Add this toolset to your Agent's toolsets list. Pydantic AI handles discovery and validation from there.

Q: What happens if the Kraken API changes unexpectedly with Pydantic AI?

Your agent will fail with a clear ValidationError. Pydantic AI guarantees that the data your agent receives matches the expected schema. This prevents silent bugs caused by upstream API changes.

Q: How do I get historical data for backtesting from Kraken using Pydantic AI?

Your agent can call the getohlc tool. The response is a validated list of candle objects. Because Pydantic AI enforces types, you can trust that fields like open, high, low, and close are always correct numbers.

Get type-safe, validated Kraken market data in your Python agent. Pydantic AI ensures every API response is correct, every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kraken MCP to Pydantic AI

Create your Vinkius account to connect Kraken 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 Kraken with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Eliminate Bad API Data

Pydantic AI's main job is to enforce correctness. When your agent calls a Kraken tool through this MCP server, the response is automatically validated against a strict Pydantic model. If the data is malformed, your code gets an exception, not corrupted results. Imagine Kraken's API temporarily returns a string instead of a number for a price in `get_ticker`. Other frameworks might fail silently or pass bad data. Pydantic AI will immediately raise a `ValidationError`, so you know exactly what broke and why.

Build Model-Agnostic Financial Bots

You're not locked into one LLM provider. Pydantic AI works with OpenAI, Anthropic, Gemini, or even local models running on your machine. You can swap the underlying model without changing how your agent interacts with the Kraken data. You could prototype a trading idea using a fast local model that analyzes `get_spread` data. Once the logic is sound, you can switch to a more powerful cloud model for deeper analysis of `get_ohlc` history, all while the tool-calling code remains identical.

A Pydantic AI Server for Reliable Market Data

This isn't just a random script. It's a managed MCP server that gives your Pydantic AI agent a stable, predictable source for Kraken data. You don't have to worry about maintaining the connection or parsing the raw API output yourself. The server handles converting raw Kraken JSON into a clean format. When you call `get_order_book`, you get a structured object with `bids` and `asks`, guaranteed. This lets you focus on your agent's logic, not on data cleaning.

Setup guide

Set up Kraken 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": {
        "kraken-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]` and instantiate `MCPToolset("http://...")` with your Vinkius server URL. Add this toolset to your `Agent`'s `toolsets` list. Pydantic AI handles discovery and validation from there.

Your agent will fail with a clear `ValidationError`. Pydantic AI guarantees that the data your agent receives matches the expected schema. This prevents silent bugs caused by upstream API changes.

Yes. Pydantic AI is model-agnostic. You can configure it to use any LLM that has a compatible adapter, including models running locally via Ollama or llama.cpp, while still getting validated Kraken data.

Your agent can call the `get_ohlc` tool. The response is a validated list of candle objects. Because Pydantic AI enforces types, you can trust that fields like `open`, `high`, `low`, and `close` are always correct numbers.

It only reads public, anonymous market data from Kraken—things like candlestick data, current prices, and recent trades. The server operates in a zero-trust environment and has no access to your personal credentials or private keys.

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