How to Use the CoinCap MCP in Google ADK

Q: Can I use CoinCap with Google ADK to run automated trading strategies?

Yes, you can write agents that monitor prices using getasset and trigger actions. The Google ADK manages the tool execution, letting your agent decide when to act based on live market feeds.

Feed real-time CoinCap market data and historical candles directly into your Google ADK pipelines for deep Gemini analysis.

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 Google ADK

Create your Vinkius account to connect CoinCap to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context crypto ingestion with Google ADK

The `get_asset_history` and `get_candles` tools feed historical market snapshots directly into Gemini's large context window. Your agent can call these endpoints repeatedly, gathering months of trading data to analyze trends without running out of memory. This MCP Server lets your Google ADK agent pull raw historical snapshots directly into its prompt context. The agent can then run complex pattern recognition across thousands of data points in a single reasoning step.

BigQuery pipelines fueled by live exchange data

The `get_exchange` and `list_exchanges` tools bridge the gap between your BigQuery warehouse tables and live market venues. An enterprise agent can verify trading venue status, then join that data with your existing cloud datasets. By exposing these tools to your LlmAgent, you bridge the gap between static cloud storage and live market realities. The agent uses `get_markets` to check active trading pairs and instantly updates your cloud databases.

Multi-currency enterprise pricing via MCP Server

The `get_rate` and `get_rates` tools check real-time fiat conversions, feeding exact math to your global billing agents. Your agents use these values to ensure your enterprise applications calculate exact asset values before generating invoices. Using the Google ADK toolset, you can restrict access to only these pricing tools. This ensures your agent stays focused on rate calculations using `get_asset` without wandering into exchange-level data.

Setup guide

Set up CoinCap MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CoinCap tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CoinCap_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CoinCap tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Yes, you can write agents that monitor prices using `get_asset` and trigger actions. The Google ADK manages the tool execution, letting your agent decide when to act based on live market feeds.

You initialize the McpToolset with the server's HTTP URL and pass it to your LlmAgent constructor. The agent automatically registers tools like `get_candles` and `list_assets` for immediate use.

Yes, you can use the optional tool names filter in the ADK to limit exposure. For instance, you can expose only `get_rate` and block exchange-related tools to keep your agent focused.

Absolutely, Gemini's long-context models are built to parse raw structured data. The JSON outputs from `get_markets` or `get_asset_history` are parsed directly by the model without requiring manual preprocessing.

All cryptocurrency price and market data queries run through an ephemeral, zero-trust sandbox in Vinkius. Your private enterprise data inside Google Cloud remains completely isolated, and no transaction data is stored.

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