How to Use the Cheddar MCP in Pydantic AI

Q: How do I connect the Cheddar server to Pydantic AI?

Install the required dependencies with pip install "pydantic-ai-slimmcp". Instantiate an MCPToolset pointing to your Vinkius HTTP URL, and append it to the toolsets list when defining your agent.

Enforce strict runtime validation on Cheddar billing responses using Pydantic AI to prevent hallucinated charges.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cheddar MCP to Pydantic AI

Create your Vinkius account to connect Cheddar 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 Cheddar with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe billing with Pydantic AI

Integrating Cheddar via Pydantic AI guarantees that every response from `get_cheddar_customer_details` matches your exact schema. Financial operations cannot tolerate silent failures or missing fields. If the API returns an unexpected string instead of a float for a balance, the framework throws a validation error immediately. You define the expected structure for customer records, and the agent enforces it at runtime. Calling `add_cheddar_charge` requires specific arguments like customer ID and amount. The model-agnostic engine validates these inputs before the HTTP request ever hits the billing system.

Unified toolset integration for MCP

The modern approach uses `MCPToolset` initialized with your Vinkius URL to grant your agent instant access to `list_cheddar_invoices` and `list_cheddar_transactions`. Deprecated server classes cause maintenance headaches. You pass this directly into the `toolsets` array of your agent. You choose between Server-Sent Events or Streamable HTTP transports based on your architecture. The external MCP Server runs independently, while your Python code focuses entirely on coordinating the logic and validating the incoming payment histories.

Strict validation for pricing and promotions

When your agent queries `list_cheddar_plans` or `list_cheddar_promotions`, the framework ensures the discount percentages map perfectly to your internal types. Quoting the wrong price to a customer creates immediate liability. The rigid schema definitions prevent these mistakes. This strictness allows you to trust autonomous billing workflows. The agent retrieves the core configuration with `get_cheddar_product_info`, validates the structural integrity of the payload, and proceeds to calculate usage-based fees without hallucinating random coupon codes.

Setup guide

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

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

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

Install the required dependencies with `pip install "pydantic-ai-slim[mcp]"`. Instantiate an `MCPToolset` pointing to your Vinkius HTTP URL, and append it to the `toolsets` list when defining your agent.

The framework catches every structural anomaly. If the invoice payload lacks a required date or total amount, the runtime validation fails loudly rather than passing corrupt data to your downstream logic.

The framework remains entirely model-agnostic. You can run Llama locally or connect to Anthropic, and the agent will still parse `list_cheddar_customers` outputs into your defined schemas with the exact same rigor.

That specific class is deprecated in newer versions. Stick to the unified `MCPToolset` approach, which natively handles both Streamable HTTP and SSE connections to your external MCP Server.

Data validation happens locally in your Python environment. The Vinkius infrastructure simply securely proxies the raw payment amounts and customer IDs through a zero-trust sandbox. No financial information is logged or retained on the managed servers.

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