How to Use the Kraken MCP in Google ADK

Q: How do I connect Google ADK to the Kraken MCP server?

After you pip install google-adk, create an McpToolset instance pointing to your Vinkius server URL. Pass that toolset into your LlmAgent constructor. The ADK handles the rest.

Q: Can I filter which Kraken tools my Google ADK agent can use?

Yes. When you create the McpToolset, you can pass an optional toolnames list. This lets you restrict the agent to only use specific tools, like getohlc and getticker, for safety.

Q: What's the best way to backtest a strategy with Google ADK and Kraken data?

Use the getohlc tool with the since parameter. You can write an agent that walks backwards in time, pulling historical candle data from Kraken chunk by chunk. It can then feed this data into a Vertex AI model for backtesting.

Connect Google ADK to live Kraken data. Feed real-time market signals directly into your BigQuery and Vertex AI pipelines.

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 Google ADK

Create your Vinkius account to connect Kraken to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Market Data into BigQuery Insights

The Google ADK is built to talk to other Google services. Connect this MCP server and you can build an agent that pulls real-time market data from Kraken and feeds it directly into BigQuery tables for large-scale analysis. Have your agent fetch hourly candles with `get_ohlc` and the latest trades with `get_trades`. It can then structure this data and insert it into a BigQuery dataset, building a historical market data warehouse automatically.

Long-Context Reasoning with Gemini

Gemini models can handle huge amounts of information. This lets your agent analyze complex market scenarios without losing track of the details. You can feed it an entire order book and ask for a deep analysis. Use an agent to pull the full depth of the order book with `get_order_book(count=500)`. Gemini can process the entire raw response to identify support and resistance levels, calculate slippage, and summarize liquidity distribution in a single pass.

A Reliable MCP Server for Google ADK

This isn't just a random script. It's a managed MCP server that gives your 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. Start your agent's workflow by calling `get_asset_pairs` to get a complete list of tradable assets on Kraken. From there, it can systematically query `get_ticker` for each one, or use `get_asset_info` to check which assets can be used as collateral.

Setup guide

Set up Kraken MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Kraken tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Kraken_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kraken tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

After you `pip install google-adk`, create an `McpToolset` instance pointing to your Vinkius server URL. Pass that toolset into your `LlmAgent` constructor. The ADK handles the rest.

Yes. When you create the `McpToolset`, you can pass an optional `tool_names` list. This lets you restrict the agent to only use specific tools, like `get_ohlc` and `get_ticker`, for safety.

Use the `get_ohlc` tool with the `since` parameter. You can write an agent that walks backwards in time, pulling historical candle data from Kraken chunk by chunk. It can then feed this data into a Vertex AI model for backtesting.

Absolutely. The large context window is a perfect fit. You can pull a massive trade history with `get_trades` and the full order book with `get_order_book` and feed it all to Gemini in one prompt for a deep market analysis.

This server is built for security. It only accesses public Kraken market data—prices, order book depth, and trade history. Your Google account and Kraken exchange keys are never exposed or required.

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