WebsiteCategorizationAPI
Home
Demo Tools - Categorization
Website Categorization Text Classification URL Database Taxonomy Mapper
Demo Tools - Website Intel
Technology Detector Quality Score Competitor Finder
Demo Tools - Brand Safety
Brand Safety Checker Brand Suitability Quality Checker
Demo Tools - Content
Sentiment Analyzer Context Aware Ads
MCP Servers
MCP Real-Time API MCP Database Lookup Database Lookup Setup Guide Real-Time API Setup Guide
Agentic Workflows
AI Agent Database 100 Use Cases Hedge Fund Workflows Banking Workflows Healthcare Workflows E-Commerce Workflows SaaS Workflows View All 47 Industries →
Domains By
Domains for your ICP Domains by Vertical Domains by Country Domains by Technologies
Resources
API Documentation Pricing Login
Try Categorization
MCP Server

Real-Time API Server Classify any URL in real-time using the Website Categorization API through the Model Context Protocol. Works with Claude Desktop, Claude Code, and Cursor.

7 Taxonomies
57,607 Total Categories
4 MCP Tools
8+ Enrichment Signals
Prerequisites
Python 3.10+ Required for the MCP server runtime
API Key Get yours at websitecategorizationapi.com
Git To clone the repository
MCP Client Claude Desktop, Claude Code, or Cursor
1
Clone the Repository

Clone the official MCP Real-Time API server to your local machine. This downloads the server script, configuration templates, and dependency manifest.

Terminal
git clone https://github.com/websitecategorization/mcp-realtime-api.git
cd mcp-realtime-api
View on GitHub
2
Install Dependencies

Install the required Python packages: mcp (Model Context Protocol SDK), httpx (async HTTP client), and python-dotenv (environment variable management).

Terminal
pip install -r requirements.txt
This installs mcp>=1.0.0, httpx>=0.27.0, and python-dotenv>=1.0.0. You can also install them individually: pip install mcp httpx python-dotenv
3
Set Your API Key

Create a .env file in the project directory with your API key. You can find your key on your profile page after signing up.

.env
# Required: Your API key from websitecategorizationapi.com
WCA_API_KEY=your-api-key-here
You can copy the .env.example file as a starting point: cp .env.example .env and then edit it with your actual API key.
4
Configure Your MCP Client

Add the server configuration to your preferred MCP client. Select your client below and follow the instructions.

claude_desktop_config.json
{
  "mcpServers": {
    "website-categorization-api": {
      "command": "python",
      "args": ["/full/path/to/mcp-realtime-api/wca_mcp_realtime.py"],
      "env": {
        "WCA_API_KEY": "your-api-key-here"
      }
    }
  }
}
Config file location:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Terminal
claude mcp add website-categorization-api \
  -- python /full/path/to/mcp-realtime-api/wca_mcp_realtime.py
Set the API key as an environment variable before running Claude Code:
export WCA_API_KEY="your-api-key-here"

Or add it to the .env file in the cloned repository directory.
.cursor/mcp.json
{
  "mcpServers": {
    "website-categorization-api": {
      "command": "python",
      "args": ["/full/path/to/mcp-realtime-api/wca_mcp_realtime.py"],
      "env": {
        "WCA_API_KEY": "your-api-key-here"
      }
    }
  }
}
Create the .cursor/mcp.json file in your project root directory. Cursor will automatically detect and load the MCP server when you open the project.
5
Test It

Restart your MCP client, then try these example prompts to verify everything is working.

  • "Categorize stripe.com and tell me what industry it belongs to"
  • "What is nytimes.com/politics about? Give me the IAB and IPTC categories"
  • "Batch categorize apple.com, shopify.com, and github.com"
  • "Check my remaining API credits"
  • "Categorize docs.google.com/spreadsheets with expanded categories and confidence scores"

Available Tools

The MCP server exposes four tools that your AI assistant can call automatically based on your natural language prompts.

categorize_url
Categorize a single URL in real-time. Works with both homepages and full-path subpage URLs.
categorize_url("stripe.com/pricing")
categorize_url_with_options
Categorize a URL with additional options like expanded categories and confidence scores.
categorize_url_with_options("bbc.com", expanded_categories=True)
batch_categorize
Categorize multiple URLs in a single request. Supports up to 10 URLs per batch.
batch_categorize("apple.com, stripe.com, github.com")
check_credits
Check your remaining API credits and usage statistics. No URL required.
check_credits()

Taxonomy Coverage

Every URL classification returns categories across all seven supported taxonomy standards simultaneously.

Taxonomy Categories Depth Use Case
IAB v2 698 4 Tiers Programmatic advertising, content classification
IAB v3 703 4 Tiers Latest IAB standard for digital advertising
IPTC NewsCodes 1,124 3 Tiers News and media content classification
Google Shopping 5,474 Multi-level Product categorization for e-commerce
Shopify 10,560 Multi-level Shopify product taxonomy mapping
Amazon 39,004 Multi-level Amazon product and browse node classification
Web Content Filtering 44 1 Tier Brand safety, content filtering, parental controls

Enriched Data

Beyond categorization, each API response includes rich metadata signals for deeper analysis.

Buyer Personas

Identify the target audience and buyer personas associated with the content.

Sentiment Analysis

Detect the overall sentiment (positive, negative, neutral) of the page content.

Topic Extraction

Extract the main topics and themes discussed on the page.

Keyword Identification

Identify the most relevant keywords and phrases from the content.

Named Entity Recognition

Extract named entities such as companies, people, locations, and products.

Competitor Detection

Detect competing brands, products, and services mentioned on the page.

Web Technology Stack

Identify the technologies, frameworks, and platforms powering the website.

Malware & Phishing Detection

Flag URLs associated with malware distribution or phishing attempts.

Troubleshooting

Common issues and solutions when setting up the MCP Real-Time API server.

Make sure you have set the WCA_API_KEY environment variable. You can either:
1. Create a .env file in the mcp-realtime-api directory with WCA_API_KEY=your-key
2. Add it to the "env" section of your MCP client configuration
3. Export it in your shell: export WCA_API_KEY="your-key"
1. Verify the path to wca_mcp_realtime.py is an absolute path (starts with / on macOS/Linux or C:\ on Windows).
2. Make sure python is in your system PATH. Try using python3 instead of python in the config.
3. Restart your MCP client completely after updating the configuration.
The API has a 35-second timeout. If a URL is slow to respond, the request may time out. Try again or check if the URL is accessible in your browser. Very large or complex pages may occasionally take longer to process.
The dependencies are not installed. Run pip install -r requirements.txt in the mcp-realtime-api directory. If you have multiple Python versions, make sure you install to the same Python that your MCP client is using. Try pip3 install -r requirements.txt or python -m pip install -r requirements.txt.
Your API key is invalid or has expired. Verify your key on your profile page. Make sure there are no extra spaces or quotes around the key in your .env file. If your credits are exhausted, you can purchase more at the pricing page.
The batch_categorize tool has a limit of 10 URLs per request to prevent excessive API usage. Split larger batches into groups of 10 or fewer. Each URL in the batch counts as one API credit.

Need Help?

Our team is here to help you get started with the MCP Real-Time API server. Reach out through any of the channels below.