How to Use the AwardWallet MCP in Pydantic AI

Q: How does Pydantic AI ensure the AwardWallet itinerary data is correct?

When your agent calls getuseritineraries, Pydantic AI intercepts the JSON response and validates it against a predefined Pydantic model. If there's any mismatch, it raises an error instead of passing bad data to your application.

Q: Can a Pydantic AI agent get a list of all loyalty programs from AwardWallet?

Yes, it would call the listloyaltyproviders tool. Pydantic AI guarantees the result will be a properly formatted list of provider objects, making it safe to iterate over in your code without writing extra checks.

Q: What's the setup process for using AwardWallet with a Pydantic AI agent?

It's straightforward. You install pydantic-ai-slimmcp, create an MCPToolset instance with your Vinkius server URL, and pass it to your Agent's toolsets parameter. The framework handles the rest.

Build brutally reliable agents with Pydantic AI that manage AwardWallet data. No more silent API failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AwardWallet MCP to Pydantic AI

Create your Vinkius account to connect AwardWallet 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 AwardWallet with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe Travel and Rewards Data

This MCP Server exposes tools to fetch user travel data, like `get_user_itineraries` and `get_account_history`. When you use it with Pydantic AI, every single response is automatically validated against a strict data model. If AwardWallet's API ever returns an unexpected field or a malformed date, your agent won't guess or fail silently. Pydantic AI will raise a `ValidationError` immediately. This forces you to handle data inconsistencies instead of letting them corrupt your application.

Manage Accounts with an MCP Server

Use tools like `list_connected_users` and `get_user_accounts` to manage your user base. Pydantic AI ensures the data structures you get back are exactly what your code expects. This is about building predictable systems. When your agent calls `get_account_details`, you know for a fact you're getting a specific set of fields. You don't have to write defensive code checking if a balance is a string or an integer—Pydantic AI already did the work.

Connect to Any LLM, Get Consistent Results

The AwardWallet tools, like `create_auth_url` for onboarding or `get_account_check` for status, work the same way regardless of your backend LLM. Pydantic AI is model-agnostic, so you can swap between OpenAI, Gemini, or a local model without rewriting your tool-using logic. Because Pydantic AI handles the tool definition and response parsing, the LLM's only job is to decide *which* tool to call. This separation means you can focus on the agent's reasoning, trusting that the data it gets from the AwardWallet MCP Server will always be correct.

Setup guide

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

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

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

When your agent calls `get_user_itineraries`, Pydantic AI intercepts the JSON response and validates it against a predefined Pydantic model. If there's any mismatch, it raises an error instead of passing bad data to your application.

You can use any model that Pydantic AI supports. This includes models from OpenAI, Anthropic, Google, and even open-source models you run locally. The AwardWallet tools will work the same with all of them.

Yes, it would call the `list_loyalty_providers` tool. Pydantic AI guarantees the result will be a properly formatted list of provider objects, making it safe to iterate over in your code without writing extra checks.

It's straightforward. You install `pydantic-ai-slim[mcp]`, create an `MCPToolset` instance with your Vinkius server URL, and pass it to your `Agent`'s `toolsets` parameter. The framework handles the rest.

The server only processes the data required for a specific tool call, like a user's timeline or account details. Your Vinkius endpoint encrypts all traffic, and Pydantic AI itself doesn't store this data; it just validates its structure in memory before passing it to your agent.

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