How to Use the VTEX Catalog MCP in Pydantic AI

Q: Can I use Pydantic AI to manage stock levels in VTEX Catalog?

Absolutely. You can use managestock and saveproduct. The type-safe framework ensures that the SKU, quantity, and other required parameters are correct before sending the update.

Q: Which data types does this MCP Server touch for Pydantic AI?

This server handles core catalog data: brand information (getbrand), category details (getcategory), product records, and SKU inventory counts from VTEX Catalog.

Q: How do I update product information in VTEX Catalog using Pydantic AI?

You use saveproduct. Because the framework requires strict schema adherence, it forces all inputs—like names or descriptions—to be correct before attempting to write them to your catalog.

Connect VTEX Catalog to Pydantic AI. Type-safe tool execution for guaranteed data integrity across all product management actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VTEX Catalog MCP to Pydantic AI

Create your Vinkius account to connect VTEX Catalog to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup VTEX Catalog with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Product Updates

When you run `save_product` through the Pydantic AI framework, every response is validated against a schema. If VTEX Catalog sends back unexpected data for an item, your agent fails LOUDLY—you never have silent corruption. It's designed for correctness above all else. You can confidently let your agent update products knowing that the returned structure will be correct.

Reliable Data Retrieval

Need to check a SKU? Use `get_sku`. Need general product info? Call `get_product`. The Pydantic AI framework ensures that whatever data you pull from VTEX Catalog—whether it's brand details or category structure—is typed and predictable. This type-safety is huge. It means your agent doesn't have to guess what kind of fields are coming back, making multi-step processes reliable.

Controlled Catalog Searches

The `search_products` tool lets you query VTEX Catalog by text, brand ID (`b/1234`), or category ID (`c/5678`). Because of Pydantic validation, the agent knows exactly what structure to expect when it gets search results. This predictability makes building complex multi-tool workflows—like 'search and then manage stock'—totally reliable.

Setup guide

Set up VTEX Catalog MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "vtex-catalog-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to VTEX Catalog tools.",
)

result = await agent.run("List recent VTEX Catalog transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by VTEX. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect VTEX Catalog now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about VTEX Catalog MCP in Pydantic AI

Every MCP response is validated against a Pydantic model at runtime. If the API returns unexpected fields or bad types from your VTEX Catalog, the agent throws an explicit validation error.

Absolutely. You can use `manage_stock` and `save_product`. The type-safe framework ensures that the SKU, quantity, and other required parameters are correct before sending the update.

This server handles core catalog data: brand information (`get_brand`), category details (`get_category`), product records, and SKU inventory counts from VTEX Catalog.

The agent searches your VTEX Catalog using text or IDs. The resulting list of products is validated against a model, guaranteeing you get structured, predictable data back.

You use `save_product`. Because the framework requires strict schema adherence, it forces all inputs—like names or descriptions—to be correct before attempting to write them to your catalog.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript