How to Use the Cardly MCP in AutoGen

Q: How do I load Cardly tools into AutoGen?

Install the autogen-extmcp package. Fetch the tools via mcpservertools and pass them directly to your AssistantAgent constructor.

Q: How does AutoGen handle Cardly connection errors?

A dedicated networking agent can run verifyapiconnection first. If it fails, the agent pauses the conversation to alert you instead of failing silently.

Q: Do AutoGen agents need to know the Cardly API schema?

No. The McpToolAdapter converts the server parameters automatically. Your agents just read the descriptions and know what arguments to provide.

Let your AutoGen agents debate card designs and verify addresses before shipping physical mail.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cardly MCP to AutoGen

Create your Vinkius account to connect Cardly 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 Cardly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate for Cardly orders

One agent runs `preview_greeting_card` to generate a mockup, while a separate critic agent reviews the text for typos. They argue over the layout until both agree the message looks correct. Only after reaching consensus does the primary agent execute `place_greeting_card_order`. This prevents expensive mistakes when sending actual physical mail.

Verify contacts before adding

The data-entry agent calls `find_contact` to see if an email already exists in your system. A validation agent checks the output and flags any missing fields. If the record is clean, they proceed to call `add_contact_to_list`. Splitting the lookup and creation tasks across different personas reduces duplicate entries in your address book.

Audit MCP Server budgets automatically

A finance-focused agent executes `get_account_info` to check your available balance. It cross-references this with the cost of items pulled from `list_card_artwork`. When funds drop too low, the finance agent halts the execution pipeline. It forces the system to ask a human for approval before any more physical cards get shipped.

Setup guide

Set up Cardly 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 Cardly 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="Cardly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cardly 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="Cardly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cardly 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 Cardly. 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 Cardly 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 Cardly MCP in AutoGen

Install the `autogen-ext[mcp]` package. Fetch the tools via `mcp_server_tools` and pass them directly to your `AssistantAgent` constructor.

They share the tool definitions, but usually one specific agent is assigned to execute the actual API calls while others analyze the results.

A dedicated networking agent can run `verify_api_connection` first. If it fails, the agent pauses the conversation to alert you instead of failing silently.

No. The `McpToolAdapter` converts the server parameters automatically. Your agents just read the descriptions and know what arguments to provide.

Vinkius processes all requests through a secure V8 Isolate Sandbox. The physical mailing addresses and order IDs exist only during the transaction and are wiped from memory immediately after.

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