How to Use the Cardly MCP in Pydantic AI

Q: How do I register Cardly tools in Pydantic AI?

Use MCPToolset("http://...") with your Vinkius URL. Pass this unified toolset to your Agent using the toolsets argument.

Type-safe MCP physical mail automation with Cardly and Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Cardly to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Order physical mail with strict type safety

Executing `place_greeting_card_order` requires perfectly structured address data, which Pydantic AI guarantees at runtime. If your language model hallucinates a missing zip code or invents a fake state abbreviation, the framework throws a validation error immediately. The agent fails loudly instead of sending garbage data to the printer. You test the layout by calling `preview_greeting_card` first. The response parses into a strict Pydantic model, ensuring the image URL and preview metadata actually exist before your application tries to render them.

Fetch Cardly MCP Server artwork data

Requesting `list_card_artwork` pulls the available designs into your application state. Because you define the exact schema you expect, you never deal with missing fields or silent corruption if the upstream API changes its response format. The agent drills down using `get_artwork_details` to get precise dimensions. Model-agnostic design means you can swap LLM providers anytime. The validation layer catches any provider-specific quirks before they break your app.

Manage recipient lists deterministically

Invoking `list_contact_lists` returns your address books as strongly typed objects. Your agent iterates through these lists without guessing dictionary keys or writing defensive null checks. Pushing new records via `add_contact_to_list` forces the agent to conform to exact string lengths and format requirements. You spend zero time debugging malformed API requests because the framework blocks them from leaving your machine.

Setup guide

Set up Cardly MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cardly-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Cardly tools.",
)

result = await agent.run("List recent Cardly transactions")
print(result.output)

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 Pydantic AI

Use `MCPToolset("http://...")` with your Vinkius URL. Pass this unified toolset to your Agent using the `toolsets` argument.

The model likely generated a payload that failed your schema validation. The framework intercepts bad arguments before they reach the external endpoint.

Yes. The framework does not care which LLM generates the tool call. As long as your local model outputs JSON that passes validation, it can order cards.

No. That class is deprecated in newer versions. Stick to the unified `MCPToolset` approach for both Streamable HTTP and SSE transports.

The server handles physical mailing addresses and personal contact details. Vinkius secures the transport layer with ephemeral tokens, ensuring your customer data never sits in a vulnerable middlebox.

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