Can my AI agent accept or reject incoming orders automatically?

Yes! Use `accept_order` to confirm an incoming order or `reject_order` with a reason (out_of_stock, closing_soon, too_busy, item_unavailable). Once accepted, the PedidosYa system begins assigning a delivery courier. When ready, use `mark_order_ready` to signal the courier for pickup.

How do I mark items as sold out on my live menu?

Use the `update_product_status` tool with the restaurant ID, product ID, and set `available` to false. The product will immediately show as unavailable on PedidosYa. To bring it back, call the same tool with `available` set to true.

Can I request a courier for deliveries outside of food orders?

Yes! Use the `request_courier` tool to create a shipment request with pickup and dropoff addresses. This leverages PedidosYa's logistics network for B2B courier services, independent of restaurant orders. Track the courier in real-time with `track_shipment`.

PedidosYa MCP Server for Pydantic AI 14 tools — connect in under 2 minutes

Name: PedidosYa
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 14 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect PedidosYa through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to PedidosYa "
            "(14 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in PedidosYa?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PedidosYa MCP Server

Connect your PedidosYa partner account to any AI agent and manage the full delivery lifecycle across Latin America's leading food delivery platform.

Pydantic AI validates every PedidosYa tool response against typed schemas, catching data inconsistencies at build time. Connect 14 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Order Management — Receive, accept, reject, and mark orders as ready for pickup, all through natural conversation without touching the partner tablet
Menu Control — Toggle products on/off (sold out) and update prices in real-time on your live PedidosYa listing
Courier Logistics — Request on-demand PedidosYa couriers for B2B deliveries and track their GPS position in real-time
Venue Management — Query all your registered restaurants, their operating hours, preparation times, and marketplace performance
Webhook Automation — Configure event-driven webhooks for new orders, cancellations, and courier assignments

The PedidosYa MCP Server exposes 14 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PedidosYa to Pydantic AI via MCP

Follow these steps to integrate the PedidosYa MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 14 tools from PedidosYa with type-safe schemas

Why Use Pydantic AI with the PedidosYa MCP Server

Pydantic AI provides unique advantages when paired with PedidosYa through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your PedidosYa integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your PedidosYa connection logic from agent behavior for testable, maintainable code

PedidosYa + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the PedidosYa MCP Server delivers measurable value.

Type-safe data pipelines: query PedidosYa with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple PedidosYa tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query PedidosYa and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock PedidosYa responses and write comprehensive agent tests

PedidosYa MCP Tools for Pydantic AI (14)

These 14 tools become available when you connect PedidosYa to Pydantic AI via MCP:

accept_order

Once accepted, the restaurant commits to preparing the items within the estimated preparation time. The PedidosYa system will begin assigning a delivery courier. Accept a pending order

create_webhook

g., new_order, order_cancelled, courier_assigned, order_delivered). Create a new webhook subscription

get_order

Get full details of a specific order

get_restaurant

Get details of a specific restaurant

list_menu_sections

g., Entradas, Platos Principales, Bebidas, Postres). Each section contains its products with prices, descriptions, and availability status. List menu sections and products for a restaurant

list_orders

Filter by status to find pending orders requiring acceptance, orders being prepared, orders ready for pickup, or completed deliveries. List incoming orders

list_restaurants

Each venue includes its operating status, delivery radius, and current open/closed state. List your partner restaurants

list_webhooks

). List configured webhooks

mark_order_ready

This triggers the courier dispatch if one hasn't already arrived. Mark an order as ready for courier pickup

reject_order

Valid rejection reasons include: out_of_stock, closing_soon, too_busy, item_unavailable. Frequent rejections may affect your venue's ranking on the platform. Reject a pending order

request_courier

Used for scheduling on-demand courier pickups, ideal for B2B deliveries outside the regular order flow. Specify the pickup and dropoff addresses and package details. Request a PedidosYa courier for a delivery

track_shipment

Track a courier shipment in real-time

update_product_price

Price changes take effect immediately on the marketplace listing. The price should be in the local currency of the venue's country. Update the price of a menu product

update_product_status

Use this to mark items as temporarily unavailable (sold out) or to bring them back online without editing the full menu. Toggle a menu product on or off

Example Prompts for PedidosYa in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with PedidosYa immediately.

"Show me all pending orders for my restaurant."

"Mark the Chocotorta as sold out on restaurant ID R-4421."

"Request a courier to pick up a package from Av. 18 de Julio 1234, Montevideo and deliver to Rambla Wilson 500."

Troubleshooting PedidosYa MCP Server with Pydantic AI

Common issues when connecting PedidosYa to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

PedidosYa + Pydantic AI FAQ

Common questions about integrating PedidosYa MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your PedidosYa MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.