How to Use the CoinCap MCP in OpenAI Agents SDK

Feed live cryptocurrency price feeds and market metrics directly to your OpenAI Agents SDK pipelines with zero-config tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoinCap MCP to OpenAI Agents SDK

Create your Vinkius account to connect CoinCap to OpenAI Agents SDK 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 CoinCap with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded crypto price checks with OpenAI Agents SDK

The `get_asset` and `list_assets` tools let your production agents pull real-time token valuations without custom wrappers. By exposing these endpoints directly to your agent pool, the SDK auto-discovers the tools and lets your specialized agents route queries based on the requested token. The SDK guardrails validate the outgoing arguments before hitting the CoinCap endpoints. This prevents your agents from passing malformed token IDs to `get_asset`, saving LLM tokens and avoiding API errors in your production logs.

Multi-agent historical market analysis via MCP

The `get_candles` and `get_asset_history` tools allow your supervisor agent to route macro trend analysis to specialized charting agents. One agent can watch the macro trend using `list_exchanges`, while another handles micro-level technical analysis by building structured price histories. This setup lets your supervisor agent hand off tasks to a dedicated charting agent. Because this MCP Server exposes the tools uniformly, the OpenAI Agents SDK handles the transition and keeps a clean trace of every tool call in your dashboard.

Real-time fiat conversion and trading pair auditing

The `get_rate` and `get_rates` tools feed instant conversion pairs to your trading bots for automated global pricing. Agents use these tools to calculate exact asset values against fiat currencies without manual math. When auditing exchange liquidity, the agent queries `get_markets` and `get_exchange` to find where the volume actually is. The SDK validates these multi-step tool calls, ensuring your agent doesn't execute trades based on stale or missing market data.

Setup guide

Set up CoinCap MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CoinCap tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CoinCap tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CoinCap tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CoinCap Agent",
            instructions="You have access to CoinCap tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 CoinCap. 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 CoinCap 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 CoinCap MCP in OpenAI Agents SDK

The SDK auto-discovers the tools when you register the server. You pass the server URL to MCPServerStreamableHttp and assign it to your agent, which instantly exposes tools like `get_asset` and `get_candles`.

Yes, you can control tool access at the agent definition level. While the server exposes all 9 tools, you can configure your OpenAI agent to only call specific tools like `get_rate` while ignoring exchange-level tools.

No, this setup is completely stateless. Your agents fetch live data directly from the API through the MCP Server, meaning you do not need to maintain local databases for asset prices or exchange rates.

You should handle rate limiting within your agent's execution loop or backoff logic. The server passes raw HTTP responses, so if the API limits your requests, your agent will receive the error and can retry.

Your queries pass through a secure, isolated sandbox that never logs your trade strategies or parameters. Since CoinCap requires no API keys, your agent requests run without exposing sensitive credentials or private keys.

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