Web Cat API

by Kode-Rex

309 downloads
Not rated
GitHub

About

Web Cat API is a collection of Python-based APIs that includes a Model Context Protocol (MCP) server for web search and content extraction. It integrates with Serper.dev for search capabilities and uses the readability library to extract clean text from web pages, making it easy…

Details

Author
Kode-Rex
Downloads
309
Categories
Developer Tools, Search

- Content extraction using the readability library
- Web search integrated with Serper.dev
- MCP-compliant with both SSE streaming and REST endpoints
- Configurable rate limiting and API versioning
- Docker support for simple deployment

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Web Cat API
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Run the MCP server via Docker with docker run -p 8000:8000 -e SERPER_API_KEY=your_key tmfrisinger/webcat:latest. You can also set a custom port or configure rate limiting via environment variables.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "web cat api": {
            "webcat": {
                "command": "docker",
                "args": [
                    "run",
                    "-p",
                    "8000:8000",
                    "-e",
                    "SERPER_API_KEY=your_key",
                    "tmfrisinger/webcat:latest"
                ]
            }
        }
    }
}

McpServers

{
    "webcat": {
        "command": "docker",
        "args": [
            "run",
            "-p",
            "8000:8000",
            "-e",
            "SERPER_API_KEY=your_key",
            "tmfrisinger/webcat:latest"
        ]
    }
}

Web Cat API

Introduction

Web Cat is a collection of Python-based APIs designed to enhance AI models with web search and content extraction capabilities. The project includes:

1. A serverless Python-based API hosted on Azure Functions
2. A Model Context Protocol (MCP) server that provides web search capabilities for AI models

Both implementations are designed to responsibly scrape and process website content, making it easy to integrate web content into AI applications like ChatGPT through Custom GPTs.

Components

Azure Functions API

The Azure Functions API leverages the readability library and BeautifulSoup to extract the main body of text and related images from web pages.

MCP Server

The Model Context Protocol (MCP) server is a FastAPI-based implementation that provides web search capabilities with enhanced content extraction. It follows the MCP specification for standardized AI model interactions.

Features

- Content Extraction: Utilizes the readability library for clean text extraction - Text Processing: Further processes extracted content for improved usability - Search Functionality: Integrates with Serper.dev to provide web search capabilities - MCP Compliance: Follows standardized Model Context Protocol specifications - Multiple API Styles: Supports both Server-Sent Events (SSE) streaming and RESTful endpoints - Rate Limiting: Protects the API from abuse with configurable rate limits - API Versioning: Ensures backward compatibility as the API evolves - Docker Support: Easy deployment with Docker containers - Parallel Processing: Faster response times with parallel search result processing

Getting Started

Azure Functions API

- See the customgpt directory for specific documentation

MCP Server (Docker)

- Current version: 1.1.0 - Docker image: tmfrisinger/webcat:1.1.0 or tmfrisinger/webcat:latest

Running with Docker

```bash
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.