How to Use the Cardly MCP in OpenAI Agents SDK

Q: How do I connect Cardly to the OpenAI Agents SDK?

Initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass it to the Agent constructor using the mcpservers argument. Tools discover themselves automatically.

Q: Does this MCP Server support caching?

Set cacheToolsList=True in your server configuration. This stops the agent from refetching the tool definitions on every single run.

Build production-ready MCP greeting card pipelines with Cardly and the OpenAI Agents SDK.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate physical mail via OpenAI Agents SDK

Your agent uses `place_greeting_card_order` to dispatch real physical mail based on system events. You define triggers in your Python application, and the model handles address formatting and message generation. Built-in guardrails ensure nobody accidentally orders ten thousand birthday cards because of a logic bug. Before spending money, configure the agent to call `preview_greeting_card`. This generates a visual proof of the printed item. The handoff feature lets a specialized review agent check the preview against brand guidelines before passing execution back to the ordering agent.

Browse and select card designs dynamically

Calling `list_card_artwork` pulls the current inventory of greeting card designs directly into your OpenAI agent's context window. The agent filters options based on the occasion, recipient profile, or sentiment analysis of the intended message. You get full visibility into this selection process through the OpenAI tracing dashboard. Once a design looks promising, `get_artwork_details` fetches the exact dimensions and orientation requirements. Text generation prompts adapt automatically to fit the physical constraints of the chosen card. Nothing gets cut off at the printer.

Manage recipient lists from your logic

Executing `add_contact_to_list` pushes new customer addresses straight into your Cardly address book. You'll tie this MCP Server to your CRM webhooks, letting the agent format and store contact data without human intervention. The agent queries `list_contact_lists` to find the right grouping for holiday campaigns or onboarding sequences. It maps new signups to the correct physical mailing tier automatically. Every operation runs securely inside your deployed environment.

Setup guide

Set up Cardly 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 Cardly tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cardly 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="Cardly Agent",
            instructions="You have access to Cardly 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 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 OpenAI Agents SDK

Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass it to the Agent constructor using the `mcp_servers` argument. Tools discover themselves automatically.

Yes. You write custom guardrails that intercept the tool call. The agent evaluates the address format before it ever hits the ordering endpoint.

The SDK catches the error and logs it in your tracing dashboard. Your agent can retry the request or hand off to a fallback agent to alert a human.

Set `cacheToolsList=True` in your server configuration. This stops the agent from refetching the tool definitions on every single run.

This server touches physical mailing addresses and personal names. Vinkius isolates the connection in an ephemeral V8 sandbox, so your recipient data never leaks to unauthorized agents.

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