Manual: How to Connect your AI to Icecat MCP (example Claude Desktop App)

Version 1.3 (Updated on June 16th, 2026)

As an example for how to integrate the Icecat MCP server into an AI, this guide provides step-by-step instructions on how to install and configure the Claude Desktop App to connect with Icecat MCP using an API Access Token.

Icecat MCP enhances LLMs with accurate knowledge about product data, thus avoiding the weak spots of AI: hallucinations. With Icecat MCP, you can be sure that a chatbot will provide accurate data.

Data scope notice: Icecat MCP tools return product data only for Icecat sponsor brands. Queries for non-sponsor products will return empty results — this is expected behaviour, not a bug.

Check the full list of sponsor brands →

1. Prerequisites

Before you begin, make sure you have a registered Icecat account with the channel partner user type.

A channel partner account can be created on the Registration page. These users access product datasheets through Icecat Pull APIs (XML, JSON, CSV, Live HTML) using a Full or Open Icecat subscription.

If you have an account for managing products on Brand Cloud, you won’t be able to use Icecat MCP. Please create a channel partner account — it’s free of charge.

⚠️ Fair Use Policy — AI training prohibition
Access to Icecat MCP is subject to the Open Icecat Fair Use Policy. Product data retrieved via MCP must not be used to train, fine-tune, or optimize AI or machine learning models. Violations constitute a material breach of your license.

2. Install Required Software

1. Download and Install the Claude Desktop App
2. Download and Install Node.js

3. Obtain Your Icecat API Access Token

1. Log in to your Icecat account.
2. Go to My profile settings.
3. Scroll down to the Access Tokens section.
4. Click on Manage Access Tokens.
5. Either:
   • Create a new API Access Token, or
   • Copy an existing one.

Account tier and MCP access: Both Open Icecat and Full Icecat account holders have equal access to MCP at this stage. The MCP currently returns sponsor brand data only, regardless of your account tier. Account tier distinctions may become relevant in future MCP releases.

⚠️ Important: Keep your API token secure. Do not share it with unauthorized persons.

🔍 Access Tokens as an Alternative to IP Whitelists and app_key

4. Configure Claude Desktop App

You need to update a configuration file named claude_desktop_config.json.

1. Follow Settings > Developer > Local MCP Servers and click on Edit Config, and you will be redirected to the folder you need to place your config file in.

2. Update or create the configuration file in the Claude Desktop directory. It usually already exists as an empty JSON file.
3. ⚠️ Make sure the file extension is .json and not .txt.

Insert the following content into the file claude_desktop_config.json:

 {
  "mcpServers": {
    "icecat-mcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.icecat.biz",
        "--header",
        "Api-Token:YOUR_API_TOKEN",
        "--header",
        "Lang-Code:en"
      ]
    }
  }
}

1. Replace YOUR_API_TOKEN with the Icecat API Access Token.
2. Replace en in the Lang-Code line with the desired language code to get information for that locale. This parameter is optional. If not specified, 🇬🇧 EN will be used as the fallback locale. 🔍 Check the Icecat Locales and Language Code Table
3. Save the file.

5. Disable AI Training in Claude

As a condition of the Open Icecat Fair Use Policy, product data retrieved via Icecat MCP must not be used to train AI models. By default, Claude may use your conversations as training data, so you must turn this off before using Icecat MCP.

Follow these steps:

1. Open the Claude Desktop App or go to claude.ai and log in.
2. Click your profile name or icon (bottom-left of the sidebar).
3. Click Settings.
4. Navigate to Privacy.
5. Find the toggle labelled “Help improve our AI models”.
6. Switch it OFF.

✅ Once disabled, your conversations and the Icecat product data within them will not be used to train Anthropic’s AI models.

⚠️ Important limitation: Conversations you had before disabling this setting may already have been used for training. The opt-out applies to new and resumed conversations going forward. For maximum protection, avoid opening old conversations that contained Icecat data.

⚠️ Note for Free, Pro, and Max users: This setting is on by default and must be turned off manually. Enterprise and API users are automatically exempt from training data collection.

Note: The steps above reflect the Claude interface as of June 2026. Anthropic may update their settings layout at any time. If the flow has changed, refer to Anthropic’s current privacy settings documentation for the latest instructions.

6. Finalize Setup

1. Restart the Claude Desktop App. ⚠️ Make sure to close it also on the tray.
2. On the next launch, the app will automatically connect to Icecat MCP using your configuration.
3. You can verify that you are connected to the MCP by clicking on Settings:

Claude requires permission to use the external MCP and each of the tables; allowing it once means that each new message (not chat) pop-up will appear again.

7. Input Product Identifiers

In the current stage Icecat MCP supports all standard Icecat Identifiers. The AI agent must provide the either:

• ProductCode
• Brand
• GTIN – considered the highest prio identifier. If provided, other identifiers are ignored.

8. Output Tools Overview

The main purpose of Icecat MCP is to enhance your Language models with accurate information about the products. It allows an AI agent to access the verified information provided in the following tools.

Text Tools

product_identifiers – The AI agent uses this tool when the user asks for basic product identifiers. Includes basic information:

• Brand
• Product code
• GTINs
• Title
• Model
• Category

product_lifecycle – The AI agent uses this tool when the user asks for product Release and End of Life dates

product_description – The AI agent uses this tool when the user asks for descriptive or promotional product information. Includes:

• Marketing text
• Official product naming
• Summaries
• Disclaimers
• Bullet Points

product_specs – The AI agent uses this tool when the user asks for detailed product specs, features, and feature groups.

product_overview – The AI agent uses this tool when the user asks for a general overview of available product details in one response. Includes basic information from all other tools.

product_warranty – The AI agent uses this tool when the user asks about warranty information.

product_reasons_to_buy – The AI agent uses this tool when the users asks to provide the product advantages or reasons to buy.

product_review – The AI agent uses this tool when the user ask to provide user reviews for the product.

product_related – The AI agent uses this tools when the user asks for similar or supplementatary products (up-sell and cross-sell).

Multimedia Tools

⚠️ Icecat MCP always provide links to physical files, not files as an attachment.

product_manual – The AI agent uses this tool when the user asks about manuals, returns Manual PDF.

product_certificates – The AI agent uses this tool when the user asks about safety documents. Returns following multimedia assets:

• Carbon Footprint
• Repairability Index
• Durability Index
• CE Marking
• EU & UK Energy Labels
• EU Product Fiche
• EU & UK Declaration of Conformity
• Safety Data Sheet

product_leaflet – The AI agent uses this tool when the user asks about marketing leaflet, returns Leaflet.

product_video – The AI agent uses this tool when the user asks about Videos.

product_360_view – The AI agent uses this tools when the user asks about 360 degree view.

product_story – The AI agent uses this tools when the user asks about Product Stories or visual promo materials.

product_additional_documents – The AI agent uses this tools when the user asks about other PDFs or complete set of supplementary documents.

Please check 🔍 Multimedia overview manual to view examples for each Multimedia type.

Gallery Tool

product_gallery – The AI agent uses this tool when the user asks about images, pictures or product gallery, returns links to images in different resolutions.

Please check 🔍 How to Make the Product Gallery Great Again to learn more about gallery.

Analytics tool

product_analytics – The AI agent uses this tool when the user asks about product popularity analytics. Provides total product downloads from Icecat.

Brand Contacts

product_brand_contacts — The AI agent this tool when the user asks about brand contacts and regulatory data, typically in the context of GPSR compliance.

More about GPSR: 🔍Manual: Retrieving GPSR related Contact Details.

9. Troubleshooting

Icecat connector does not appear in Claude settings

1. Check whether the Node.js is installed. In your OS terminal the command node -v should return the version of installed Node.js.
2. Check whether the file claude_desktop_config exists in Claude root folder and has JSON format.
3. Restart the Claude, make sure to close the application in tray as well.

MCP Connection Errors

10. Use-cases

For example, you want to check what kind of Bluetooth is supported by the product Philips SHB9850NC/00. Instead of checking this manually, you can ask Claude.

With Icecat MCP, AI must check the data in our tables before sending it. Therefore, the chatbot will always provide accurate information about the product or clarify that Icecat does not have the product data.

An example of how Claude checks product specs before providing an answer to the customer’s question.

Try it now

1. Which of the following notebooks should I choose to combine software development with gaming: Lenovo / 21X20021AU or DELL / X11D4?
2. Generate a short and catchy description for the toothbrush Philips / HX6932/10 based on its overview to be used in my promo materials.
3. Analyze the promo materials provided by the supplier and overviews to describe the target audience for my social media targeting. Brand: Samsung, Product Codes: SM-F956BZSCEUE, SM-F741BLBGEUB, SM-G780FLVDEUE, SM-G925FZKAITV, SM-F741BZSGEUB, SM-S908BZGDEUE, SM-S906BZWDEUE, SM-F926BZKDEUA
4. Compare the popularity of these three monitors and recommend which one I should feature as “Gamer’s Choice” in my store: LG / 27GP850-B, Samsung / LS34BG850SUXEN, DELL / S2722QC
5. I’m selling in the EU. Retrieve all safety documentation and EU energy labels for the washing machine Gorenje / 741266. I need to verify my product page meets EPREL and GPSR requirements.
6. Create 3 short Instagram Reels captions (under 100 characters each) highlighting unique features of the gaming mouse Logitech / 910-004843. Make them fun and Gen-Z friendly.
7. Use the style and coloring scheme from ProductStory in product Nerf F63975L0 to create a banner for my Summer sales.

11. More about AI in Icecat

🔍 Icecat MCP server: Enhance your AI with World-Class Product Intelligence

🔍 AgenticFlow: how to integrate your own AI Agent with Icecat MCP

🔍 Mindpal: How to integrate your own AI Agent with the icecat MCP

🔍 How to integrate your BoltAI Desktop app with Icecat MCP