4,500+ servers built on MCP Fusion
Vinkius
AMcards logo
Vinkius
OpenAI Agents SDK logo

How to Use the AMcards MCP in OpenAI Agents SDK

Use the OpenAI Agents SDK to have your agents send real, handwritten cards with AMcards and track their delivery status.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

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

Connect AMcards MCP to OpenAI Agents SDK

Create your Vinkius account to connect AMcards 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

Send Cards Directly From Your Agent

Your agent can now send physical greeting cards. The OpenAI Agents SDK automatically discovers the AMcards tools, so your agent can call `send_greeting_card` with a contact's details and a personalized message. It feels like adding a new Python function, but it triggers a real-world action. This isn't just for one-off tasks. You can build specialized agents that manage entire outreach sequences. Use the built-in guardrails to require human confirmation before a card is sent, or have one agent propose a campaign and another approve it. You can see the full trace of these actions in your OpenAI dashboard, from the `trigger_drip_campaign` call to the final status check with `get_card_sending_history`.

Integrate AMcards with the OpenAI Agents SDK

Your agent won't be guessing what it can do. The SDK's auto-discovery finds every available tool on this MCP Server, from `list_card_templates` to `list_drip_campaigns`. This means your agent knows exactly which card designs and automated campaigns are available before it tries to send anything. Because you're building a production system, you need reliability. The agent framework lets you set up handoffs between different agents—one for drafting messages, another for selecting the right AMcards template. The whole process is traceable, so you can debug why an agent chose a specific card or campaign.

Full Tracing for Every Action

The `check_api_health` tool lets your agent confirm the AMcards service is online before attempting any operations. It's a simple but critical check for building a resilient system. You can build this into your agent's startup routine or as a pre-flight check before running a big campaign. Every tool call your agent makes—`list_configured_webhooks`, `get_card_sending_history`, anything—is logged in the OpenAI dashboard. This gives you a clear, step-by-step trace of your agent's decisions and actions. If a card fails to send, you'll know exactly which step failed and why, without digging through server logs.

Setup guide

Set up AMcards 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. 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. 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 AMcards tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AMcards 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="AMcards Agent",
            instructions="You have access to AMcards tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by AMcards. 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 AMcards MCP in OpenAI Agents SDK

Just pass the AMcards MCP Server to the Agent constructor. The OpenAI Agents SDK handles tool discovery automatically. Your agent can then call `send_greeting_card` like any other function.
Yes. While the SDK auto-discovers all tools, you can implement guardrails and validation logic within your agent code to restrict access to certain functions, like `trigger_drip_campaign`. You have full control over the agent's permissions.
It can. For better performance in production, set `cacheToolsList=True` when you configure the server connection. This stops the agent from refetching the tool list on every run.
Your agent simply calls the `list_card_templates` tool. The MCP Server returns a current list of all available card designs that AMcards can send.
The server only processes recipient contact information and message content needed to send a card via `send_greeting_card`. All data is transmitted over encrypted channels, and the Vinkius platform runs each server in an ephemeral, zero-trust sandbox. Your auth token is the only key.

Start using the AMcards MCP today

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

Built & Managed by Vinkius 30s setup 7 tools

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

No hosting. No infrastructure. No complex setup.
All 7 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.