CoinCap MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect CoinCap through 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="CoinCap Assistant",
instructions=(
"You help users interact with CoinCap. "
"You have access to 9 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from CoinCap"
)
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 CoinCap MCP Server
Connect to CoinCap APIs and access real-time cryptocurrency market data through natural conversation — no API key needed.
The OpenAI Agents SDK auto-discovers all 9 tools from CoinCap through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries CoinCap, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Asset Prices — Get current prices, market caps, 24h volume and supply info for any cryptocurrency
- Asset Search — Search for crypto by name or symbol (Bitcoin, Ethereum, Solana, etc.)
- Historical Prices — Retrieve price history with configurable intervals (1m to 1d)
- Markets — See which exchanges list specific trading pairs and their 24h volumes
- Exchange Rankings — Browse exchanges ranked by 24h volume with verification status
- OHLCV Candles — Get candlestick data for technical analysis with multiple timeframes
- Exchange Rates — View crypto-to-fiat conversion rates
The CoinCap MCP Server exposes 9 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 CoinCap to OpenAI Agents SDK via MCP
Follow these steps to integrate the CoinCap 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 9 tools from CoinCap
Why Use OpenAI Agents SDK with the CoinCap MCP Server
OpenAI Agents SDK provides unique advantages when paired with CoinCap 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
CoinCap + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the CoinCap MCP Server delivers measurable value.
Automated workflows: build agents that query CoinCap, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries CoinCap, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through CoinCap tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query CoinCap to resolve tickets, look up records, and update statuses without human intervention
CoinCap MCP Tools for OpenAI Agents SDK (9)
These 9 tools become available when you connect CoinCap to OpenAI Agents SDK via MCP:
get_asset
Returns the current price in USD, market cap, 24h trading volume, price change percentages (1h, 24h, 7d), circulating supply, total supply, max supply and rank. Asset IDs are lowercase with hyphens (e.g. "bitcoin", "ethereum", "solana"). Get detailed info for a specific cryptocurrency
get_asset_history
Returns daily or interval-based price snapshots. Use interval to specify the data granularity: "m1" (1 minute), "m5" (5 min), "m15" (15 min), "m30" (30 min), "h1" (1 hour), "h2" (2 hours), "h6" (6 hours), "h12" (12 hours), "d1" (1 day). Get historical price data for a cryptocurrency
get_candles
Each candle includes the open, high, low, close prices and volume for the time interval. Supports intervals: "m1", "m5", "m15", "m30", "h1", "h2", "h6", "h12", "d1". Optionally set start/end timestamps (milliseconds since epoch) for historical data. Get OHLCV candlestick data for technical analysis
get_exchange
Returns the exchange name, website, 24h volume, number of markets, rank, verification status and supported assets. Exchange IDs are lowercase (e.g. "binance", "coinbase-pro", "kraken"). Get detailed info for a specific cryptocurrency exchange
get_markets
Each market includes the exchange ID, base asset ID, quote asset ID, trading pair symbol, current price, 24h volume in USD and volume percentage. Optionally filter by asset ID or exchange ID. Get trading markets/pairs for assets or exchanges
get_rate
Returns the current rate for converting the asset to its corresponding fiat currency. Base IDs are typically asset IDs like "bitcoin", "ethereum" or fiat codes like "USD". Get a specific exchange rate
get_rates
). Returns the rate ID, symbol, currency symbol and current rate. Optionally filter by base currency. Get exchange rates for cryptocurrencies to fiat currencies
list_assets
Optionally search by name, filter by specific IDs, and paginate with limit/offset. Returns assets sorted by market cap by default. List cryptocurrency assets with prices and market data
list_exchanges
Each exchange includes its ID, name, website, 24h volume in USD, number of markets, rank and whether it's verified. List cryptocurrency exchanges with rankings
Example Prompts for CoinCap in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with CoinCap immediately.
"What is the current price of Bitcoin?"
"Show me the top 5 cryptocurrency exchanges by volume."
"Show me the 1-hour candlestick data for Ethereum."
Troubleshooting CoinCap MCP Server with OpenAI Agents SDK
Common issues when connecting CoinCap to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
CoinCap + OpenAI Agents SDK FAQ
Common questions about integrating CoinCap 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 CoinCap 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 CoinCap to OpenAI Agents SDK
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.