Can I see a preview of the card before sending it?

Yes! Use the `preview_greeting_card` tool with your message and artwork ID. Your agent will return a preview URL (usually a PDF) so you can verify everything looks perfect.

How do I find the correct artwork ID for a design?

Simply ask the agent to `list_card_artwork`. It will retrieve all the available designs from your account, including their titles and unique IDs or slugs.

Does the integration support international shipping?

Yes. When using the `place_greeting_card_order` action, you can specify the country code (e.g., 'UK', 'AU', 'US'). Cardly handles the local printing and postage automatically.

Cardly MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: Cardly
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Cardly through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Cardly "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Cardly?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cardly MCP Server

Connect your Cardly account to any AI agent and orchestrate your personalized gifting, customer appreciation, and physical mail workflows through natural conversation.

Pydantic AI validates every Cardly tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Order Management — Place real orders for physical greeting cards with custom messages and designs directly from your workspace.
Design Oversight — Browse your custom artwork library and retrieve detailed metadata for individual designs.
Order Preview — Generate a watermarked PDF preview of your card to verify content and layout before sending.
Contact Coordination — Access and manage your contact lists and add new recipients to your address book.
Global Shipping — Send cards to recipients in the US, Australia, UK, and worldwide with automatic address validation.
API Verification — Verify your connection and API key status instantly using the echo tool.

The Cardly MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cardly to Pydantic AI via MCP

Follow these steps to integrate the Cardly MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from Cardly with type-safe schemas

Why Use Pydantic AI with the Cardly MCP Server

Pydantic AI provides unique advantages when paired with Cardly through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Cardly integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Cardly connection logic from agent behavior for testable, maintainable code

Cardly + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Cardly MCP Server delivers measurable value.

Type-safe data pipelines: query Cardly with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Cardly tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Cardly and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Cardly responses and write comprehensive agent tests

Cardly MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect Cardly to Pydantic AI via MCP:

add_contact_to_list

Add a new contact to a specific list

find_contact

Search for a contact in a list by email

get_account_info

Retrieve core account information

get_artwork_details

Get details of a specific piece of artwork

list_card_artwork

List available greeting card designs/artwork

list_contact_lists

List all contact lists in your account

place_greeting_card_order

Place a real order for a physical greeting card

preview_greeting_card

Generate a preview of a greeting card without placing a real order

verify_api_connection

Verify connectivity and API key validity

Example Prompts for Cardly in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Cardly immediately.

"List all the available greeting card designs in my account."

"Preview a card with artwork art_1 and message 'Happy Birthday John!'."

"Send a thank you card to Jane Smith in Australia."

Troubleshooting Cardly MCP Server with Pydantic AI

Common issues when connecting Cardly to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Cardly + Pydantic AI FAQ

Common questions about integrating Cardly MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Cardly MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.