Kraken Trading Bot in Python

This guide shows how to build a Kraken trading bot in Python with LumiBot, for both AI agent trading and algorithmic trading. LumiBot connects to Kraken through CCXT, the open source library that talks to more than 100 crypto exchanges. You will create a Kraken account and API key, connect it, and run two examples: a simple algorithmic trading bot and an agentic trading bot where an AI agent makes the calls.

What BotSpot MCP adds

Use Claude, ChatGPT, Codex, Cursor, VS Code or another MCP-compatible assistant? Connect the free BotSpot MCP for:

  • Skills: build LumiBot strategies.

  • Free data: news, economics and SEC filings.

  • Backtests: run tests and read charts.

  • Cloud hosting: low-cost scheduled bots.

  • Community: share bots and discuss trades.

  • Marketplace: discover and publish strategies.

  • Broker linking: connect accounts through BotSpot.

Connect your AI assistant

Kraken at a glance

CCXT exchange id

kraken

Markets

Spot, Margin

Testnet (sandbox)

No

Credentials

API key, API secret

Live data streams

prices, order book, trades, candles, your orders, your balance

CCXT request spacing

about 1000 ms between requests

Official site

https://www.kraken.com

API docs

https://docs.kraken.com/api-reference/

Fees

https://www.kraken.com/en-us/features/fee-schedule

What is Kraken?

Kraken is a crypto exchange. Its Kraken Pro platform offers spot, margin and derivatives trading on more than 400 assets. LumiBot uses Kraken’s spot API.

Sign up for Kraken

  1. Create a Kraken account (or a Kraken Pro account at https://pro.kraken.com) with your email, a username and a strong password, then open the activation email and enter the activation key.

  2. Finish verification. Kraken asks for your name, date of birth, phone number, address, occupation and a valid ID.

  3. Turn on sign-in two-factor authentication in your Security settings. Kraken recommends a passkey, and an authenticator app also works.

Open a Kraken account

Create a Kraken API key

  1. Sign in to Kraken Pro, open the account menu (the profile icon in the top right) and choose Settings.

  2. Open the API tab and click Create API key.

  3. Give the key a unique name, for example “LumiBot Trading Key”.

  4. Turn on the permissions listed below. You can also add IP whitelisting so the key only works from your bot’s IP address.

  5. Click Generate key.

  6. Save the API key and the Private key in a password manager. Kraken says to treat them like your username and password.

Which permissions to turn on: Turn on Query Funds, Query Open Orders & Trades, Query Closed Orders & Trades, Modify Orders and Cancel/Close Orders. Access WebSockets API is also safe to turn on. Leave Withdraw Funds off. Kraken’s own example says a trading key almost certainly does not need it, and a bot never needs to move money out of your account.

Warning

Never turn on withdrawals for a Kraken trading bot key. Bind the key to your server’s IP address when Kraken lets you, keep the secret out of your code and out of Git, and delete the key if it ever leaks.

Connect Kraken to LumiBot

The simplest way: put these lines in a .env file next to your strategy. LumiBot loads the file, sees TRADING_BROKER=kraken and connects to Kraken for you, so your strategy needs no broker code.

TRADING_BROKER=kraken
KRAKEN_API_KEY=your_apiKey
KRAKEN_API_SECRET=your_secret

LumiBot reads exactly the fields CCXT needs for Kraken (apiKey, secret). If one is missing, LumiBot stops at start-up and names the variable you still need.

You can also build the broker in code. This is handy when one script talks to more than one exchange, or when you need extra CCXT options. The keys in the config are CCXT’s own credential names for Kraken:

import os

KRAKEN_CONFIG = {
    "exchange_id": "kraken",
    "apiKey": os.environ.get("KRAKEN_API_KEY"),
    "secret": os.environ.get("KRAKEN_API_SECRET"),
    "sandbox": False,  # live connection
}

from lumibot.brokers import Ccxt

broker = Ccxt(KRAKEN_CONFIG)
# then: MyStrategy(broker=broker, ...)

Either way, LumiBot turns on CCXT’s built-in rate limiting for you.

Testing on Kraken

Kraken has no spot sandbox, and LumiBot’s Kraken path has no sandbox switch, so test with a very small amount. In a code config, set "sandbox": False.

Algorithmic trading example: a simple Kraken bot

This bot buys about 50 USD of BTC on Kraken once and then holds it. It is a starting point to check that your keys, balances and orders work. If the exchange’s minimum order is larger, raise the amount. Kraken accepts only limit orders through CCXT, so the example places a limit order just above the last price.

from lumibot.entities import Asset
from lumibot.strategies import Strategy


class KrakenBuyOnce(Strategy):
    """Buy a small amount of BTC once, then hold it."""

    def initialize(self):
        self.sleeptime = "1H"
        self.set_market("24/7")  # crypto trades all day, every day

    def on_trading_iteration(self):
        coin = Asset("BTC", asset_type=Asset.AssetType.CRYPTO)
        if self.get_position(coin) is not None:
            return  # already holding BTC
        price = self.get_last_price(coin, quote=self.quote_asset)
        if price:
            quantity = round(50 / price, 6)  # about 50 USD worth
            # This exchange takes only limit orders through CCXT.
            order = self.create_order(coin, quantity, "buy", limit_price=price * 1.002, quote=self.quote_asset)
            self.submit_order(order)


if __name__ == "__main__":
    # LumiBot reads TRADING_BROKER and the keys from your .env file.
    strategy = KrakenBuyOnce(quote_asset=Asset("USD", asset_type=Asset.AssetType.CRYPTO))
    strategy.run_live()

Agentic trading example: an AI agent that trades on Kraken

Agentic trading means an AI agent reads the market and decides what to do. In this example one LumiBot agent looks at prices and your Kraken account, then places the orders itself. There is no Python logic in between: you set the rules in plain English in the prompt, such as what it may trade and how big each order can be. This follows the same pattern as LumiBot’s AI trading team examples.

from lumibot.entities import Asset
from lumibot.strategies import Strategy


class KrakenAITrader(Strategy):
    """One AI agent researches the market and places the trades itself."""

    def initialize(self):
        self.sleeptime = "4H"
        self.set_market("24/7")
        self.agents.create(
            name="trader",
            model="openai/gpt-6-luna",
            reasoning_effort="high",
            allow_trading=True,
            system_prompt=(
                "You manage a small crypto account on Kraken. "
                "You may trade BTC and ETH against USD (asset_type 'crypto', quote_symbol 'USD'), or hold cash. "
                "Before every order, call account_portfolio, account_positions and "
                "market_last_price for that exact symbol in the same run. "
                "Keep each order under 10% of the account value. "
                "Explain each decision in one short paragraph."
            ),
        )

    def on_trading_iteration(self):
        self.agents["trader"].run(
            task_prompt="Review recent BTC/USD and ETH/USD prices and your current holdings, then decide whether to buy, sell or hold.",
            context={"exchange": "Kraken", "quote": "USD", "date": self.get_datetime().isoformat()},
        )


if __name__ == "__main__":
    # LumiBot reads TRADING_BROKER and the keys from your .env file.
    strategy = KrakenAITrader(quote_asset=Asset("USD", asset_type=Asset.AssetType.CRYPTO))
    strategy.run_live()

The agent needs a model key such as OPENAI_API_KEY in your environment. See the AI agents quickstart for models, tools and memory.

What you can trade on Kraken

Market

Listed by CCXT

Spot

Yes

Margin

Yes

Perpetual swaps

No

Dated futures

No

Options

No

CCXT lists these order features for Kraken: stop orders, editing open orders, canceling orders.

Fees and partner IDs on Kraken

You pay Kraken’s normal trading fees. LumiBot may attach its own exchange partner ID. That costs you nothing extra. LumiBot never adds an extra builder fee unless one is turned on, and it logs a warning when one is.

Kraken tips

  • With environment variables, LumiBot reads KRAKEN_API_KEY and KRAKEN_API_SECRET. Kraken calls the secret the Private key.

  • Do not add two-factor authentication to the API key itself. Kraken explains that key 2FA only works if the software sends the 2FA code with every call, and LumiBot (through CCXT) does not send it, so every private call would fail.

  • Kraken lets you set a Key Expiration date. If you use one, plan to make a new key before it runs out, or your bot will stop logging in.

  • This page covers Kraken spot. Kraken futures is a separate exchange in CCXT with its own id, krakenfutures, and its own keys.

Frequently asked questions

Can I build a Kraken trading bot in Python?

Yes. Install LumiBot (pip install lumibot), set your Kraken keys and use the kraken CCXT exchange id as shown above.

Does Kraken have a testnet?

No testnet is set up for Kraken in LumiBot. Start with a small amount, and in a code config set "sandbox": False.

Which API permissions does a Kraken bot need?

Turn on Query Funds, Query Open Orders & Trades, Query Closed Orders & Trades, Modify Orders and Cancel/Close Orders. Access WebSockets API is also safe to turn on. Leave Withdraw Funds off. Kraken’s own example says a trading key almost certainly does not need it, and a bot never needs to move money out of your account.

Can an AI agent trade on Kraken by itself?

Yes. The agentic example above gives one agent permission to trade. You control what it may trade and how much through its prompt.

Can I trade Kraken perpetual futures with LumiBot?

CCXT does not list perpetual swaps for Kraken, so use spot markets.

Is LumiBot free?

Yes. LumiBot is open source on GitHub at https://github.com/Lumiwealth/lumibot. You pay only your exchange’s trading fees and, for AI agents, your model provider.

Run it in the cloud with BotSpot

Do not want to keep a computer running for your Kraken bot? BotSpot is the hosted home for LumiBot strategies and AI trading agents: build with AI, backtest, connect a broker, and watch every trade with logs and alerts.

Try BotSpot

Sources