Kraken MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Kraken through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Kraken Assistant",
instructions=(
"You help users interact with Kraken. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Kraken"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Kraken MCP Server
Connect to Kraken and access real-time cryptocurrency market data through natural conversation — no API key needed for public data.
The OpenAI Agents SDK auto-discovers all 8 tools from Kraken through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Kraken, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Live Tickers — Get current prices, 24h volume, VWAP and high/low for any trading pair
- OHLC Candles — Retrieve candlestick data with multiple timeframes (1m to 15d)
- Order Book — View current bids and asks with market depth analysis
- Recent Trades — See the most recent completed trades with price, volume and side
- Asset Info — Get details about all supported cryptocurrencies and fiat currencies
- Trading Pairs — Explore all available trading pairs with their specifications
- Spread Data — Analyze bid/ask spreads for liquidity assessment
The Kraken MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Kraken to OpenAI Agents SDK via MCP
Follow these steps to integrate the Kraken MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 8 tools from Kraken
Why Use OpenAI Agents SDK with the Kraken MCP Server
OpenAI Agents SDK provides unique advantages when paired with Kraken through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Kraken + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Kraken MCP Server delivers measurable value.
Automated workflows: build agents that query Kraken, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Kraken, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Kraken tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Kraken to resolve tickets, look up records, and update statuses without human intervention
Kraken MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect Kraken to OpenAI Agents SDK via MCP:
get_asset_info
Returns asset name, alternate names, decimals, status and collateral support. Optionally filter by specific assets (comma-separated). Get information about Kraken assets
get_asset_pairs
Returns pair name, alt name, base/quote assets, lot volume decimals, pair decimals, order minimums and trading leverage. Optionally filter by a specific pair. Get information about Kraken trading pairs
get_ohlc
Each candle includes time, open, high, low, close, VWAP, volume and trade count. Supports intervals: 1 (1min), 5, 15, 30, 60 (1h), 240 (4h), 1440 (1d), 10080 (1w), 21600 (15d). Optionally provide since timestamp for incremental data. Get OHLCV candlestick data for a trading pair
get_order_book
Each level includes price and volume. The count parameter controls the number of levels returned (1-500, default 100). Useful for analyzing market depth and liquidity. Get the current order book for a trading pair
get_server_time
Returns the Unix timestamp and RFC 1123 time. Useful for synchronizing with the exchange server and verifying API connectivity. Get Kraken server time
get_spread
Returns recent spreads with bid price, ask price, time (Unix timestamp) and volume. Useful for analyzing liquidity and trading costs. Get recent spread data for a trading pair
get_ticker
Returns best bid/ask prices, last trade price, 24h volume, VWAP, high/low prices and trade counts. Pair names can be standard (XBTUSD) or alt (BTCUSD). Multiple pairs comma-separated. Get current ticker information for trading pairs
get_trades
Each trade includes price, volume, time (Unix timestamp), side (buy/sell), order type (market/limit) and misc info. Returns up to 1000 most recent trades. Optionally provide since timestamp for pagination. Get recent trades for a trading pair
Example Prompts for Kraken in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Kraken immediately.
"What is the current price of Bitcoin in USD?"
"Show me the 1-hour OHLC for Ethereum over the last 24 candles."
"What are the recent trades for SOL/USD?"
Troubleshooting Kraken MCP Server with OpenAI Agents SDK
Common issues when connecting Kraken to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Kraken + OpenAI Agents SDK FAQ
Common questions about integrating Kraken MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Kraken with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Kraken to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.