How to Use the Square MCP in Pydantic AI

Q: What is the best way to retrieve customer information with Square and Pydantic AI?

Use getcustomer or searchcustomers. The agent forces the response into a defined Pydantic model. This means you get predictable Python objects every time, regardless of minor changes in the underlying Square API.

Q: Can I reliably get order details using Square and Pydantic AI?

Yes. By defining a schema for getorderdetails, the agent ensures that all necessary components—like line items, tax amounts, and discount codes—are present and correctly typed in the final object.

Validate critical commerce data with Pydantic AI on the MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Square MCP to Pydantic AI

Create your Vinkius account to connect Square to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Square with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Ensure payment data is always correct

The primary benefit here is validation. When you call `create_payment`, the agent doesn't just send the request; it validates the expected response structure against a Pydantic model. If Square sends unexpected fields, the agent fails loud and tells you exactly why. Similarly, when fetching payment history using `get_payment_details`, every single field—from transaction IDs to final amounts—must match your defined schema or the process stops.

Validate customer records on retrieval

You can guarantee data integrity for user profiles. When running a search via `search_customers` or getting details with `get_customer`, Pydantic forces the response to conform to your exact schema. You never get silently corrupted fields. This is critical when pairing customer records with order metadata from `get_order_details`. The agent ensures that the client ID in both responses aligns perfectly.

Structure inventory and catalog data

Inventory needs to be predictable. When checking stock using `get_stock_count`, the Pydantic framework forces a consistent output format, making your subsequent code reliable. Likewise, when calling `list_catalog` or listing all items, the structured validation ensures that every item record contains required fields like SKU and price, preventing downstream errors.

Setup guide

Set up Square 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": {
        "square-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Square 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 Square. 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 Square 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 Square MCP in Pydantic AI

You define a strict schema around the payment response. The agent calls `create_payment`, and if the returned data structure doesn't match your model, it throws an explicit validation error instead of passing bad data to your application.

Use `get_customer` or `search_customers`. The agent forces the response into a defined Pydantic model. This means you get predictable Python objects every time, regardless of minor changes in the underlying Square API.

The core mechanism is runtime schema validation. Every tool's output (like `list_payments` results) must pass through your defined models before your agent accepts it, guaranteeing type safety across the board.

The server touches Customer Data (contact info, purchase history). Because of the strict validation, you can be highly confident that only structured, expected fields are processed by your agent.

Yes. By defining a schema for `get_order_details`, the agent ensures that all necessary components—like line items, tax amounts, and discount codes—are present and correctly typed in the final object.

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