VTEX Catalog MCP. Manage Product Data and Inventory in Natural Conversation
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
The VTEX Catalog MCP Server lets you manage your entire product catalog—from searching products and checking SKU details to updating inventory levels—all through natural conversation with your AI agent.
You don't have to log into the admin panel to audit stock or update pricing; you just ask for it.
What your AI agents can do
Get brand
Retrieves detailed information about a specific brand ID in your catalog.
Get category
Gets the full structure and details for a specified category ID.
Get product
Fetches all specifications and metadata for a specific product ID.
Run full-text searches across the product catalog using keywords, brand IDs, or category IDs.
Get detailed information on a specific product ID, including all associated SKUs, dimensions, and metadata.
Adjust the available quantity of any SKU across multiple logistics warehouses in real time.
Send structured data to create new products or update existing ones directly in the VTEX catalog.
Check specific SKU attributes like price, weight, dimensions, EAN, and current stock status.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
VTEX Catalog MCP Server: 7 Tools for E-commerce Control
Use these seven tools to perform every kind of catalog operation imaginable: search products, update inventory, and modify core product data.
019d761dget brand
Retrieves detailed information about a specific brand ID in your catalog.
019d761dget category
Gets the full structure and details for a specified category ID.
019d761dget product
Fetches all specifications and metadata for a specific product ID.
019d761dget sku
Looks up detailed attributes (price, weight, EAN) for an exact SKU number.
019d761dmanage stock
Updates the available quantity count for a specific product SKU across your warehouses.
019d761dsave product
Creates or modifies an entire product record using structured data input.
019d761dsearch products
Finds multiple products by running a search query against text, brand IDs (b/...), or category IDs (c/...).
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with VTEX Catalog, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're gonna manage your entire product catalog—from finding a specific widget to updating warehouse stock counts—without ever touching the admin panel. This VTEX Catalog MCP Server lets your AI agent run full CRUD operations against your whole inventory using natural conversation. You just ask for it, and it gets done.
Searching and Listing Products:
You don't need to know the exact product ID; you can simply search across your entire catalog using keywords, brand IDs (b/...), or category IDs (c/...). The system immediately returns complete listings for every match. These results give you a quick view of pricing, current availability, and images for all items that fit your criteria.
Retrieving Full Product Specs:
Need the deep dive on one item? You can use get_product to pull up every piece of metadata associated with a specific product ID. This includes all linked SKUs, dimensions, categorization details, and general specifications—it's like getting an entire spec sheet in seconds.
Checking Specific Product Details (SKUs):
If you only know the SKU number, get_sku gives you the granular truth. You can check specific attributes like the retail price, weight, EAN barcode, and current stock status for that exact item. This tool lets you verify details quickly without needing to navigate through multiple product pages.
Catalog Structure Lookups:
Before you create or modify anything, you gotta know how your catalog is set up. Use get_category to pull the full hierarchical structure and details for any specified category ID. Similarly, if you need brand information, get_brand retrieves detailed data about a specific brand ID.
Creating and Updating Products:
Don't manually input data into forms. You can use structured inputs with save_product to either build an entirely new product record or overwrite details on an existing one. Just send the structured data through your agent, and it reflects immediately in the VTEX catalog.
Managing Inventory Levels:
This is critical: inventory control. The manage_stock tool lets you adjust the available quantity for any specific SKU across multiple logistics warehouses in real time. You don't have to log into the main dashboard; just tell your agent how much stock needs changing, and it handles the updates instantly.
It’s simple: Use your AI client to ask questions or send commands—whether you need to search for a product by name, update five SKUs across three locations, or create an entire new item. The server executes the complex API calls needed behind the scenes. You'll get accurate, real-time data and instant changes without ever leaving your chat interface.
How VTEX Catalog MCP Works
- 1 Subscribe to the VTEX Catalog server. You'll need your VTEX Account Name, App Key, and App Token (find these in Account Settings -> Application Keys).
- 2 Connect this server to your preferred AI client (Claude, Cursor, etc.).
- 3 Ask your agent a question—like 'Update stock for SKU 789 to 200' or 'Search for running shoes.' The agent calls the right tool and returns the result.
The bottom line is you feed your VTEX credentials once, and then your AI client handles all the API calls using plain English instructions.
Who Is VTEX Catalog MCP For?
This is for product owners, inventory planners, and merchandisers. Specifically, it helps folks who are tired of switching between the VTEX Admin dashboard, Google Sheets, and multiple internal systems just to audit or update a single line item. You need this if your job requires managing high-volume catalog data without clicking through ten nested menus.
Using the agent for save_product and search_products. They create new product lines or update bulk metadata without navigating complex admin forms.
Running real-time stock adjustments using manage_stock. They check SKU availability across different warehouses instantly when a sales forecast changes.
Using get_category and get_brand to map out the current product hierarchy. This helps them ensure new products are classified correctly before publishing.
What Changes When You Connect
- Stop switching tabs to audit stock. Use
manage_stockto adjust inventory levels for an SKU across all warehouses instantly, without opening the VTEX Admin panel. - Don't manually build product pages. Pass structured data to
save_product, and your agent writes or updates entire products in one go. - Need to know how a product is organized? Use
get_categoryandget_brand. You instantly see the parent/child relationships, which is key for merchandising plans. - Forget hunting through massive dashboards. The
search_productstool lets you find matching products by keywords or structured IDs (b/..., c/...) in a single query. - Get immediate product specs. Instead of clicking into a product and then another tab for SKUs, use
get_productto pull everything—dimensions, metadata, etc.—in one data chunk.
Real-World Use Cases
The end-of-day inventory audit
An Inventory Planner needs to know if a bulk order of running shoes (SKU 4567) arrived. Instead of logging into the warehouse system and cross-referencing, they ask their agent: 'Check SKU 4567 stock.' The get_sku tool returns the real-time count, letting them confirm availability immediately.
Launching a new product line
A Catalog Manager has gathered all specs for a new jacket. Rather than manually filling out forms and waiting for approval, they feed the data into save_product. The agent sends it to VTEX, creating the product listing instantly.
Quickly finding related items
A Merchandiser needs to see all accessories sold with a specific hiking boot. They use search_products, specifying the brand ID (b/...) and looking for matching keywords, getting a list of potential add-ons.
Debugging product placement
A developer needs to ensure that all products in the 'Summer' category are correctly linked. They use get_category on the 'Summer' ID (c/...) to verify the structure and check for missing parent links.
The Tradeoffs
Trying to search and update stock in one prompt
Asking: 'Search for products, and if I find any that are low on stock, update their count.' This is too complex for a single tool call.
→
Break it up. First, use search_products to get the list of product IDs you care about. Then, loop through those results and execute manage_stock for each one individually.
Using `get_product` when you only need stock
Calling get_product just to check if an item is in stock. This wastes time pulling massive metadata that isn't needed.
→
If all you want is the count, use get_sku. It’s much faster and more direct than retrieving the entire product specification sheet.
Manually cross-referencing brand IDs
A user remembers a brand name ('Patagonia') but doesn't know its official ID, leading to failed searches.
→
First, use search_products with the keyword. Then, if you need the absolute canonical ID for later tools, run get_brand using the ID found in the initial search results.
When It Fits, When It Doesn't
Use this server if your core job involves managing product data (SKUs, inventory counts, metadata) within VTEX and requires interactions that usually take multiple clicks or API calls. Specifically: Use manage_stock whenever you need to change counts. Use save_product when you are creating or updating the master record. If you just want a quick overview of what's available by name or category, start with search_products. Don't use this if your goal is simply reading static blog content; that's outside its scope. Also, don't try to run complex data transformations (e.g., 'take all products and calculate the average profit margin'); you need external logic for that—this server only handles catalog operations.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Finding product details shouldn't require three different tabs.
Right now, if you want to audit a single item, you typically have to log into VTEX. You find the product listing, click through to see the full specs, and then open a separate tab or section just to check the current stock level for specific SKUs. It's slow, it’s fragmented, and you lose context between tabs.
With this MCP server, your agent handles it all in one go. You ask: 'Show me product 1234.' The agent calls `get_product` to get the specs, then immediately calls `get_sku` to append the current stock count—all within a single conversational response.
The VTEX Catalog MCP Server gives you immediate control over product data.
Manual updates are painful. If pricing changes, or if an entire batch of products needs to be moved to a new category, the process involves multiple logins, manual field population, and version control headaches. You're always working with stale data until someone hits 'save'.
Now you can tell your agent: 'Update product 5678 pricing to $99 and move it under brand b/123.' The server executes `save_product` in one sequence, guaranteeing the changes happen immediately and correctly.
Common Questions About VTEX Catalog MCP
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.
If I run `get_sku` or `get_product`, how does the system handle a non-existent ID? +
The agent returns a clear, structured error message immediately. You'll get specific failure codes and text confirming that the requested SKU or product ID isn't found in VTEX. This lets your workflow skip the item gracefully instead of failing entirely.
When I use `search_products`, how do I retrieve full specifications for dozens of items? +
The search results provide a summary (name, price, count). For deep specs on many products, your agent must follow up by calling the get_product tool multiple times using the specific IDs returned in the initial list. This is how you pull the full data set.
How does the `get_category` tool map out the parent-child relationship of categories? +
It provides a structured object that explicitly lists both the Parent ID and any associated child IDs. This structure is perfect for mapping complex navigational paths, ensuring you know exactly where a category fits in your store hierarchy.
What specific physical attributes can I check using the `get_sku` tool? +
The tool provides essential logistics data like weight, dimensions, and EAN barcodes. This is critical information for fulfillment planning or any system that needs precise measurements before a product ships out.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
QuickBooks Online
Connect QuickBooks to AI — query invoices, manage customers, run financial reports, and automate accounting workflows.
Xiaomi Push Service / 小米推送
Xiaomi's essential device push platform — send notifications to MIUI and Global devices via AI.
Amazon Bedrock KB
Connect your AI agent to AWS Bedrock Knowledge Bases — execute semantic searches, managed RAG, and sync vector datasources natively.
You might also like
Agility CMS
Manage and query your Agility CMS content through AI — navigate sitemaps, search lists, and fetch layouts.
Platform.ly
Grow your business with marketing automation, CRM, and analytics connected in one platform that shows what drives revenue.
Infinity Work Manager
Manage work items, boards, comments, and folders via Infinity API.