Kraken Pro MCP
Enables natural language trading and market data queries on Kraken Pro via Gemini CLI.
README
<p align="center"> <img src="kraken_mcp_logo_alt2.png" alt="Kraken MCP logo" width="200"> </p>
Kraken Pro MCP for Gemini CLI
This project provides a FastMCP server that exposes the Kraken Pro REST API as a set of tools for the Gemini CLI. This allows you to interact with your Kraken account, trade, and access market data directly from your terminal using natural language.
Features
This server exposes a comprehensive set of tools for interacting with the Kraken API, including:
- Trading:
add_order,cancel_order,amend_order,open_orders,cancel_all_orders_after - Market Data:
server_time,system_status,asset_info,tradable_asset_pairs,ticker,ohlc,order_book,recent_trades,recent_spreads
Prerequisites
- Gemini CLI
- FastMCP (
pip install fastmcp-cli) - A Kraken Pro account with API keys.
Installation
The recommended way to install this server for use with the Gemini CLI is using the fastmcp command-line tool.
-
Clone the repository:
git clone https://github.com/oilst/kraken-mcp.git cd kraken-mcp -
Set up your environment variables: Create a
.envfile in the project directory with your Kraken API keys:KRAKEN_API_KEY="your_public_key" KRAKEN_API_SECRET="your_private_base64_secret" -
Install the server: Run the following command to install the server, its dependencies, and make the tools available to the Gemini CLI:
fastmcp install gemini-cli kraken-server.py
Usage
Once installed, you can use the tools directly in the Gemini CLI. Gemini will automatically detect the appropriate tool based on your prompt.
Examples:
- "What is the current price of Bitcoin?" (uses the
tickertool) - "Place an order to buy 0.1 XBT at $50,000" (uses the
add_ordertool) - "Show me my open orders" (uses the
open_orderstool) - "Cancel order XXXXX-XXXXX-XXXXXX" (uses the
cancel_ordertool)
Tools
Here is a list of the available tools and their parameters.
Trading Tools
add_order(pair, side, ordertype, volume, price, ...): Place a new order.cancel_order(txid_or_userref): Cancel an open order.open_orders(userref, trades): Fetch open orders.amend_order(order_id, order_qty, limit_price, ...): Amend an open order.cancel_all_orders_after(timeout_seconds): Set a dead man's switch to cancel all orders.
Market Data Tools
server_time(): Get the Kraken server time.system_status(): Get the current system status.asset_info(assets, aclass): Get information about assets.tradable_asset_pairs(pairs, info): Get information about tradable pairs.ticker(pairs): Get ticker information.ohlc(pair, interval, since): Get OHLC data.order_book(pair, count): Get the order book.recent_trades(pair, since): Get recent trades.recent_spreads(pair, since): Get recent spreads.
For detailed information on the parameters for each tool, please refer to the docstrings in the kraken-server.py file.
Disclaimer
Use this tool at your own risk. The author is not responsible for any financial losses. Always test with validate=True for the add_order tool before placing real orders.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.