4,500+ servers built on MCP Fusion
Vinkius
Deck of Cards logo
Vinkius
Google ADK logo

How to Use the Deck of Cards MCP in Google ADK

Power your Gemini agents with card game logic. Connect the Deck of Cards MCP Server to Google ADK for simulations on Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Deck of Cards MCP on Cursor AI Code Editor MCP Client Deck of Cards MCP on Claude Desktop App MCP Integration Deck of Cards MCP on OpenAI Agents SDK MCP Compatible Deck of Cards MCP on Visual Studio Code MCP Extension Client Deck of Cards MCP on GitHub Copilot AI Agent MCP Integration Deck of Cards MCP on Google Gemini AI MCP Integration Deck of Cards MCP on Lovable AI Development MCP Client Deck of Cards MCP on Mistral AI Agents MCP Compatible Deck of Cards MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Google ADK

Connect Deck of Cards MCP to Google ADK

Create your Vinkius account to connect Deck of Cards 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

Build Decks for Large-Scale Simulations

The `create_new_deck` and `create_partial_deck` tools let your agent set up any card game scenario. You can generate a standard 52-card deck or specify a custom set for a specific game. Use `shuffle_new_deck` to get a randomized deck right away. This is perfect for running Monte Carlo simulations or other data-intensive analysis on Google Cloud. Since Google ADK is built for Gemini's long context, your agent can manage the state of thousands of concurrent games, using these tools to set up each one.

Manage Game State with Google ADK

Give your agent the tools to run the game. It can `draw_cards` from the deck, `add_to_pile` to create player hands, and `list_pile` to check the contents. You can even draw from a pile's top, bottom, or a random spot with `draw_from_pile`, `draw_from_pile_bottom`, and `draw_from_pile_random`. Imagine feeding the results of these actions directly into BigQuery. With Google ADK's native integrations, your agent can call a tool from this MCP server, get the result, and log it to a table for analysis in the same workflow.

Reset and Re-run Scenarios on GCP

The server provides tools to reset the board. `reshuffle_deck` randomizes the cards currently in the deck. `return_to_deck` and `return_pile_to_deck` let your agent clean up at the end of a round, putting all cards back for the next game. You can use the `tool_names` filter in Google ADK to create specialized agents. For instance, a 'dealer' agent might only have access to shuffling and drawing tools, while a 'cleanup' agent only gets the `return_...` tools. This helps you build more structured, reliable systems on Google Cloud.

Setup guide

Set up Deck of Cards 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. 1

    Install Google ADK

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

  2. 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. 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. 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 Deck of Cards 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="Deck of Cards_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Deck of Cards tools via MCP.",
    tools=mcp_tools,
)

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Deck of Cards API. 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.

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 Deck of Cards MCP in Google ADK

You'll instantiate an `McpToolset` with the Vinkius server URL and pass it to your `LlmAgent`'s `tools` parameter. Google ADK handles discovering and calling the card functions from the MCP server.
Absolutely. Gemini's large context window means your agent can track the state of many games at once. It would repeatedly use `shuffle_new_deck`, `draw_cards`, and the pile management tools from this server to run each simulation.
Yes, that's a key feature. When you configure the `McpToolset`, you can pass a `tool_names` list to expose only specific functions, like `draw_cards` and `shuffle_pile`, to a particular agent.
The `shuffle_new_deck` tool is your best bet. It creates and shuffles a new deck in a single API call, returning the new deck ID and the number of cards remaining.
The server only works with deck identifiers, card codes, and any pile names you provide. It doesn't touch any of your other Google Cloud data. All traffic is encrypted and authenticated via your Vinkius token in an isolated, zero-trust environment.

Start using the Deck of Cards MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 13 tools

We've already built the connector for Deck of Cards. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 13 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.