How do I get my VTEX API credentials?

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.

Can my agent update stock levels without opening the VTEX Admin?

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.

How does product search work with categories and brands?

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.

Can I create new products and manage my entire catalog via AI?

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.

VTEX Catalog MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: VTEX Catalog
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect VTEX Catalog through the 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 VTEX Catalog "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in VTEX Catalog?"
    )
    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 VTEX Catalog MCP Server

Connect your VTEX Catalog API to any AI agent and manage your entire product catalog through natural conversation.

Pydantic AI validates every VTEX Catalog tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the 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

Product Search — Run full-text searches across your product catalog by name, brand ID, or category ID. Returns complete product listings with pricing, availability, and images.
Product Details — Retrieve the full specification sheet of any product by ID, including all associated SKUs, categories, dimensions, and metadata.
Product Management — Create or update products directly from your agent. Send structured product data and have it reflected in your VTEX catalog immediately.
SKU Inspection — Look up specific SKUs with detailed attributes like price, weight, dimensions, EAN, and stock status.
Stock Management — Update the available quantity of any SKU across your logistics warehouses. Adjust inventory in real-time without opening the VTEX Admin.
Category & Brand Lookup — Explore your category tree and brand directory to understand how your catalog is organized and ensure correct product classification.

The VTEX Catalog MCP Server exposes 7 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 VTEX Catalog to Pydantic AI via MCP

Follow these steps to integrate the VTEX Catalog 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 7 tools from VTEX Catalog with type-safe schemas

Why Use Pydantic AI with the VTEX Catalog MCP Server

Pydantic AI provides unique advantages when paired with VTEX Catalog 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 VTEX Catalog integration code

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

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

VTEX Catalog + Pydantic AI Use Cases

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

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

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

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

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

VTEX Catalog MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect VTEX Catalog to Pydantic AI via MCP:

get_brand

Get details of a brand

get_category

Get details of a category

get_product

Get full details of a specific product

get_sku

Get details of a specific SKU

manage_stock

Update the available quantity of a SKU

save_product

Create or update a product

search_products

Examples: "Coca Cola", "b/1234" (brand ID), "c/5678" (category ID). Search for products by text, brand, or category

Example Prompts for VTEX Catalog in Pydantic AI

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

"Search for 'Nike Air Max' in my VTEX catalog"

"Update the stock of SKU 12345 to 150 units"

"Show me the details of category 5678"

Troubleshooting VTEX Catalog MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

VTEX Catalog + Pydantic AI FAQ

Common questions about integrating VTEX Catalog 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 VTEX Catalog MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.