How to Use the Conekta MCP in Pydantic AI

Q: Does Pydantic AI validate the currency field for Conekta orders?

Yes, when the agent calls createorder, the framework checks that the payload matches the expected schema. It defaults to MXN and requires unit prices to be in cents.

Build type-safe billing agents with Pydantic AI to validate Conekta payment payloads and customer data 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 Conekta MCP to Pydantic AI

Create your Vinkius account to connect Conekta 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 Conekta with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe order creation with Pydantic AI

By using `create_order` with Pydantic AI, every customer name, email, and price in cents is validated against strict MCP schemas at runtime. Here's the thing: you don't want your LLM guessing how to format Mexican currency. If your agent attempts to pass an invalid currency or missing line items, the framework raises a validation error immediately. You get clean, predictable payment processing without silent failures.

Structured customer lookups and profile matching

Your agent runs `search_customer_by_email` and `get_customer` to fetch payment sources and order histories with complete type safety. The MCP Server returns structured JSON that matches your Python models. This ensures your code can safely access fields like customer emails and payment statuses without key errors.

Validate subscription plans and order lists

The agent calls `list_subscription_plans` and `list_orders` to pull active subscriptions and recent transactions for quick audits. Every record returned from Conekta gets parsed and validated. It keeps corrupted API payloads from breaking your database updates.

Setup guide

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

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

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

Install the MCP extension, then initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the toolsets parameter of your Pydantic AI Agent.

Yes, when the agent calls create_order, the framework checks that the payload matches the expected schema. It defaults to MXN and requires unit prices to be in cents.

The framework raises standard validation or connection errors. Your agent catches these exceptions to retry the request or log the failure safely.

Yes, Pydantic AI is model-agnostic. You can connect your Vinkius-hosted tools to local models or commercial providers like Anthropic and OpenAI.

Customer details and order data are handled entirely in memory and validated locally. Vinkius provides an ephemeral, zero-trust MCP environment to process these transactions securely.

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