How to Use the Deck of Cards MCP in AutoGen

Q: Can agents create custom card decks?

Yes, an agent can call createpartialdeck to generate a deck with only face cards. It then passes this deck to the other agents for the simulation.

Let AutoGen agents debate card strategies, manage piles, and execute game moves using real-time deck states.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deck of Cards MCP to AutoGen

Create your Vinkius account to connect Deck of Cards to AutoGen 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 Deck of Cards with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate card draws

The `draw_cards` tool pulls a set of cards from the active deck for your AutoGen agents to evaluate. One agent draws the cards while another analyzes the probability of winning the hand. They debate the next move in a group chat. Once they agree, they call `return_to_deck` to discard or keep playing based on their consensus.

Coordinate multi-agent pile management with this MCP Server

The `add_to_pile` tool lets your AutoGen agents organize cards into separate piles. A dealer agent manages the main deck while player agents maintain their own piles. The dealer agent calls `shuffle_pile` to randomize a player's discard pile. This MCP Server ensures all agents access the same synchronized state.

Execute complex card shuffles via agent consensus

The `shuffle_new_deck` tool creates a freshly randomized deck for the simulation. Your agents discuss how many decks to use before triggering the tool. If an agent suspects cheating, it calls `draw_from_pile_bottom` to verify the pile state. The agents then compare notes to ensure the game remains fair.

Setup guide

Set up Deck of Cards MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Deck of Cards tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Deck of Cards_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Deck of Cards data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Deck of Cards_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Deck of Cards data")
    print(result.messages[-1].content)

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 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.

Connect Deck of Cards 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 Deck of Cards MCP in AutoGen

They pass the active deck ID through their conversation context. When one agent calls `draw_cards`, it updates the shared deck ID so the next agent can call `list_pile` on the same deck.

Yes, you assign different agents to represent different players. They use `draw_from_pile` and `add_to_pile` to interact with the shared deck in a turn-based debate.

If an agent tries to draw from an empty deck, the server returns an error. The AutoGen agents then discuss the error and call `reshuffle_deck` to recover.

Yes, an agent can call `create_partial_deck` to generate a deck with only face cards. It then passes this deck to the other agents for the simulation.

The server only transmits card codes, deck IDs, and pile names. Your agents' conversation logs and strategy debates remain entirely private within your local AutoGen environment.

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