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 CrewAI 14 tools — connect in under 2 minutes

Name: PedidosYa
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 14 Tools Framework

Connect your CrewAI agents to PedidosYa through Vinkius, pass the Edge URL in the `mcps` parameter and every PedidosYa tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

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

from crewai import Agent, Task, Crew

agent = Agent(
    role="PedidosYa Specialist",
    goal="Help users interact with PedidosYa effectively",
    backstory=(
        "You are an expert at leveraging PedidosYa tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in PedidosYa "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 14 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

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.

When paired with CrewAI, PedidosYa becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call PedidosYa tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

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 CrewAI 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 CrewAI via MCP

Follow these steps to integrate the PedidosYa MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 14 tools from PedidosYa

Why Use CrewAI with the PedidosYa MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with PedidosYa through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

PedidosYa + CrewAI Use Cases

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

Automated multi-step research: a reconnaissance agent queries PedidosYa for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries PedidosYa, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain PedidosYa tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries PedidosYa against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

PedidosYa MCP Tools for CrewAI (14)

These 14 tools become available when you connect PedidosYa to CrewAI 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 CrewAI

Ready-to-use prompts you can give your CrewAI 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 CrewAI

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

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

PedidosYa + CrewAI FAQ

Common questions about integrating PedidosYa MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.