Bring Product Catalog
to CrewAI

Log in to your VTEX Admin, go to Account Settings → Application Keys, and create a new App Key. You'll receive an App Key and App Token pair. You also need your Account Name (the subdomain you use to access the VTEX Admin, e.g., 'mystore'). Ensure the key has Catalog and Logistics read/write permissions. No code, no SDK — just connect and go.

Yes! Use the 'manage_stock' tool with a SKU ID and the new quantity. Your agent updates the inventory balance in real-time through the VTEX Logistics API — perfect for warehouse teams receiving shipments who need to update stock counts without navigating to the Inventory module.

The 'search_products' tool supports three search modes: full-text (e.g., 'Nike Running Shoes'), by brand ID (e.g., 'b/1234'), or by category ID (e.g., 'c/5678'). This means your agent can quickly audit all products under a specific brand or explore an entire product category — no manual catalog browsing required.

Absolutely. The 'save_product' tool lets your agent create or update products by sending a structured JSON body. Combined with 'get_category' and 'get_brand' for classification, your agent can handle the full product lifecycle — from initial creation to SKU-level stock adjustments — ideal for merchandising teams managing large VTEX catalogs with thousands of products.

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.

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.

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.

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.

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.

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

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

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

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