How to Use the VTEX Catalog MCP in CrewAI

Q: How does CrewAI handle searches against VTEX Catalog?

You define a search task for your crew. One agent uses searchproducts with the input criteria (text, brand ID, etc.), and the results are passed to the next agent for analysis.

Q: Does CrewAI support retrieving product details from VTEX Catalog?

The team can retrieve full data by having an agent call getproduct with a specific ID. This provides deep context that other tools might miss, allowing for richer analysis.

Build autonomous e-commerce operations using VTEX Catalog with CrewAI's multi-agent teams.

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 CrewAI

Create your Vinkius account to connect VTEX Catalog to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Product Data Lifecycle

Let your crew manage the product lifecycle without intervention. One agent can call `get_brand` to research a brand, while another uses that ID in `search_products` to find associated items. A third specialized agent takes those results and calls `save_product`, creating or updating the catalog entry based on predefined rules.

Multi-step Catalog Analysis

You can build a research pipeline. Agent A finds an item using `get_sku` for its specific details. Agent B then uses that data to call `get_category`, confirming the proper grouping. This sequential execution makes reporting easy. It's designed for monitoring: if one tool fails, the monitor agent can flag it and escalate the task.

Team-Driven Stock Management

The crew handles inventory updates in a specialized manner. One agent might check current stock using `get_sku`, determining that an update is necessary. Another agent then executes `manage_stock` with the new count. This role-based specialization ensures that the entire process—from checking to updating—is documented and auditable.

Setup guide

Set up VTEX Catalog MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke VTEX Catalog tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="VTEX Catalog Analyst",
    goal="Access and analyze VTEX Catalog data via MCP.",
    backstory="Expert analyst with direct VTEX Catalog access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent VTEX Catalog transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="VTEX Catalog Analyst",
        goal="Access and analyze VTEX Catalog data via MCP.",
        backstory="Expert analyst with direct VTEX Catalog access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent VTEX Catalog transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

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 CrewAI

You define a search task for your crew. One agent uses `search_products` with the input criteria (text, brand ID, etc.), and the results are passed to the next agent for analysis.

Yes. You assign a role to an agent specifically responsible for calling `manage_stock`. The crew then executes this action, completing the cycle from check to update.

The team can retrieve full data by having an agent call `get_product` with a specific ID. This provides deep context that other tools might miss, allowing for richer analysis.

You set up specialized roles (e.g., Researcher, Action Taker). The crew then runs autonomously—the monitor agent watches, and the action agent performs the calls like `get_category` or `get_brand`.

The server handles identifiers including brand names, category IDs, and product details. The framework's shared memory ensures that only necessary context is passed between the collaborating agents.

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