How do I get a Nuvemshop Access Token and Store ID?

Go to the [**Nuvemshop Developer Portal**](https://dev.nuvemshop.com.br/), create an application, and follow the OAuth 2.0 Authorization Code flow to generate your access token. The token format is `AT-{store_id}-{hash}`. Your Store ID is the numeric part of the token or can be found in your store URL/dashboard settings. Use both the access token and store ID to authenticate API requests.

What are the API rate limits and how can I avoid hitting them?

Nuvemshop uses a Leaky Bucket algorithm with a default limit of 2 requests/second and a burst maximum of 40. Next and Evolution plans have this limit multiplied by 10. Monitor the `x-rate-limit-remaining` header in responses. If you hit the limit, the API returns HTTP 429. To avoid this, implement request queuing and respect the rate limit headers in your integrations.

Can I create orders manually through the API?

Yes! Use the `create_order` tool with customer information and order items. This is perfect for phone orders, in-person sales, bulk order imports, or orders from other sales channels. You need to provide at minimum the customer email and at least one item with product ID and quantity. The order will appear in your Nuvemshop dashboard as a manual order.

How do I manage product variants like size and color?

Use `list_variants` with a product_id to see all variants for a product. Each variant has its own SKU, price, and stock quantity. Variants are created when you set up product options (like size or color) in the product creation or update process. The API handles variants as part of the product object, and you can manage inventory for each variant individually.

Nuvemshop MCP Server for CrewAI 24 tools — connect in under 2 minutes

Name: Nuvemshop
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 24 Tools Framework

Connect your CrewAI agents to Nuvemshop through Vinkius, pass the Edge URL in the `mcps` parameter and every Nuvemshop 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="Nuvemshop Specialist",
    goal="Help users interact with Nuvemshop effectively",
    backstory=(
        "You are an expert at leveraging Nuvemshop 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 Nuvemshop "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 24 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 Nuvemshop MCP Server

Connect your Nuvemshop store to any AI agent and take full control of your e-commerce operations through natural conversation.

When paired with CrewAI, Nuvemshop becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Nuvemshop 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

Product Management — List, create, update, and delete products with full catalog details including variants, SKUs, and stock levels
Order Processing — Monitor orders, track fulfillment status, create manual orders, and update order states through the sales pipeline
Customer Management — Browse customer database, view order history, create and update customer records with addresses
Discount Coupons — Create, manage, and delete promotional coupons with percentage, absolute, or shipping discounts
Category Organization — List product categories to understand your store's organization structure
Variant Management — Inspect product variants (size, color, material) with individual SKUs, prices, and stock
Store Configuration — View store details including plan, currency, domain, and settings
Webhook Integration — List, create, and delete webhooks for real-time event notifications

The Nuvemshop MCP Server exposes 24 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 Nuvemshop to CrewAI via MCP

Follow these steps to integrate the Nuvemshop 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 24 tools from Nuvemshop

Why Use CrewAI with the Nuvemshop MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Nuvemshop 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

Nuvemshop + CrewAI Use Cases

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

Automated multi-step research: a reconnaissance agent queries Nuvemshop 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 Nuvemshop, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Nuvemshop 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 Nuvemshop against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Nuvemshop MCP Tools for CrewAI (24)

These 24 tools become available when you connect Nuvemshop to CrewAI via MCP:

create_coupon

You must provide the coupon code and type (percentage, absolute, or shipping). Optional fields include value, validity dates, minimum purchase amount, and applicable products/categories. Example: { "code": "SUMMER20", "type": "percentage", "value": 20, "min_price": 100, "start_date": "2026-06-01", "end_date": "2026-06-30" } Create a new discount coupon in your Nuvemshop store

create_customer

You must provide at minimum the customer name and email. Optional fields include phone, addresses, and tags. Example: { "first_name": "João", "last_name": "Silva", "email": "joao@example.com", "phone": "11999999999" } Create a new customer record in your Nuvemshop store

create_order

Useful for phone orders, in-person sales, or bulk order imports. You must provide customer information and at least one order item with product ID or variant ID and quantity. Example: { "email": "customer@example.com", "items": [{ "product_id": 123, "quantity": 2 }] } Create a new order manually in your Nuvemshop store

create_product

You must provide at minimum the product name and price. Optional fields include description, SKU, stock quantity, categories, images, and variants. Example: { "name": "T-Shirt Blue", "price": 49.90, "sku": "TSH-BLU-001", "stock": 100, "description": "Comfortable cotton t-shirt" } Create a new product in your Nuvemshop store

create_webhook

You must provide the URL to receive notifications and the events to subscribe to. Available events include: orders/create, orders/update, products/create, products/update, products/delete, customers/create, customers/update. Example: { "url": "https://your-app.com/webhooks/nuvemshop", "event": "orders/create" } Create a new webhook for real-time event notifications

delete_coupon

You must provide the coupon_id. This action cannot be undone. Use this to deactivate expired or discontinued promotions. Be careful as this will prevent customers from using this coupon code. Delete a discount coupon from your Nuvemshop store

delete_product

You must provide the product_id. This action cannot be undone. Use this to remove discontinued products, test products, or items that are no longer available. Be careful as this will also remove all associated variants and images for that product. Delete a product from your Nuvemshop store

delete_webhook

You must provide the webhook_id. This action cannot be undone. Use this to remove webhook endpoints that are no longer needed or to stop receiving notifications for specific events. Delete a webhook from your Nuvemshop store

get_coupon

Use the coupon_id obtained from list_coupons to inspect full coupon details. Get detailed information about a specific coupon

get_customer

Use the customer_id obtained from list_customers to inspect full customer details. This is useful for customer support, order management, or analyzing purchase history. Get detailed information about a specific customer

get_order

Use the order_id obtained from list_orders to inspect full order details. This is useful for verifying order status, preparing shipments, or reviewing customer purchases. Get detailed information about a specific order

get_product

Use the product_id obtained from list_products to inspect full product details. This is useful for verifying product data before updating or checking stock levels. Get detailed information about a specific product

get_store

Use this to verify your store setup and understand available features. Get details about your Nuvemshop store

list_categories

Each category includes name, description, and number of assigned products. Use this to understand your store's product organization and category structure. List all product categories in your Nuvemshop store

list_coupons

Each coupon includes code, type (percentage, absolute, shipping), value, validity dates, usage count, and minimum purchase requirements. Use this to review active promotions and analyze coupon performance. List all discount coupons in your Nuvemshop store

list_customers

Each customer includes name, email, phone number, total orders, total spent, and registration date. You can optionally specify page number and records per page. Use this to browse your customer database, analyze purchase patterns, or find specific customers by name or email. List all customers in your Nuvemshop store

list_orders

Each order includes order number, customer name, total value, status (pending, paid, fulfilled, cancelled), payment status, and creation date. You can optionally filter by status, specify page number, and set records per page. Use this to monitor sales, track order fulfillment, and review revenue. List all orders in your Nuvemshop store

list_products

Each product includes name, description, price, SKU, stock quantity, status (active, draft, archived), and images. You can optionally filter by status, specify page number, and set records per page (max: 200). Use this to browse your product catalog or find a specific product by name or SKU. List all products in your Nuvemshop store

list_variants

Each variant includes SKU, price, stock quantity, and option values. Use the product_id from list_products to see all variants of that product. This is useful for managing inventory of products with multiple options. List all variants for a specific product

list_webhooks

). Each webhook includes URL, events subscribed, and creation date. Use this to verify your integration endpoints are properly configured. List all webhooks configured in your Nuvemshop store

update_coupon

Common updates include changing discount value, extending validity dates, or modifying minimum purchase requirements. You must provide the coupon_id and the fields to update as JSON. Update an existing discount coupon

update_customer

Common updates include changing contact information, updating addresses, or adding tags. You must provide the customer_id and the fields to update as JSON. Only provide the fields you want to change. Update an existing customer record

update_order

Common updates include changing order status (e.g., from pending to paid, or from paid to fulfilled), updating shipping information, or modifying order items. You must provide the order_id and the fields to update as JSON. Update an existing order in your Nuvemshop store

update_product

You must provide the product_id and the fields to update as JSON. Only the fields provided will be updated. Common updates include: changing price, updating stock quantity, modifying description, or changing product status. The product_id must exist in your store. Update an existing product in your Nuvemshop store

Example Prompts for Nuvemshop in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Nuvemshop immediately.

"Show me all pending orders and their total values."

"Create a new coupon SUMMER20 with 20% discount, minimum purchase of R$ 100, valid until June 30th."

"List all products with stock below 10 units so I can reorder."

Troubleshooting Nuvemshop MCP Server with CrewAI

Common issues when connecting Nuvemshop 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.

Nuvemshop + CrewAI FAQ

Common questions about integrating Nuvemshop 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.