How to Use the Leal MCP in Pydantic AI

Build type-safe loyalty workflows in Python using Pydantic AI to validate every Leal API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leal MCP to Pydantic AI

Create your Vinkius account to connect Leal 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 Leal with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate member profiles at runtime

The `get_member` tool retrieves structured customer profiles and immediately validates them against your runtime schemas. Using Pydantic AI ensures that any missing fields or unexpected data types in the customer record trigger an immediate validation error instead of silently corrupting your application state. This strict validation prevents your agent from processing corrupted profiles when running automated retention campaigns. If the API returns an unexpected format, your system catches it instantly, protecting your downstream databases from dirty data.

Ensure reward catalogs match strict schemas

The `list_rewards` tool pulls the current catalog of loyalty rewards directly into your agent's decision engine. Because Pydantic AI enforces strict data models, you can guarantee that every reward item has a valid points price and store ID before displaying it to a user. This type safety eliminates the risk of your agent offering expired or mispriced rewards to customers. If a reward structure changes upstream, your agent fails loudly, allowing your team to update your schemas before customers notice.

Track customer transactions with this Pydantic AI MCP Server

The `list_transactions` tool provides a validated stream of customer purchase logs for your loyalty application. Running this tool through our MCP Server guarantees that every transaction amount, timestamp, and point value matches your expected Python types exactly. Your agent can safely calculate customer lifetime value or reward tiers based on this validated transaction history. You don't have to write manual parsing code, as the framework handles all JSON deserialization and validation automatically.

Setup guide

Set up Leal 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": {
        "leal-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You import the unified toolset class and pass the Leal HTTP endpoint URL directly. Then, add the toolset to your agent instance to instantly expose all 12 loyalty tools with strict schema validation.

The framework raises a validation error immediately if the API response doesn't match the expected schema. This prevents your agent from acting on malformed points balances or corrupted member profiles during automated campaigns.

Yes, the framework is completely model-agnostic, allowing you to use OpenAI, Anthropic, or Gemini. Regardless of the model, the Leal tool responses are validated against the same strict Python schemas before execution.

Yes, this MCP Server supports both Streamable HTTP and SSE transports for real-time updates. You just need to ensure the external server is running and accessible from your Python environment.

All loyalty points balances and customer profiles retrieved from the API are processed directly within your application's secure memory space. Vinkius runs the server in an isolated sandbox, meaning your API credentials and customer data are never cached or exposed to external entities.

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