mcp-multimodel-webscraper

TechSuvam/mcp-multimodel-webscraper

3.1

If you are the rightful owner of mcp-multimodel-webscraper and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

This project is a Model Context Protocol (MCP) server that provides tools for web scraping, sentiment analysis, and text generation using Python.

Tools
3
Resources
0
Prompts
0

Simple Multi-Model Web Scraper MCP Server

This project is an example of a Model Context Protocol (MCP) server that exposes multiple tools for web scraping, sentiment analysis, and text generation using Python.

Features

  • scrape_webpage: Fetches the title and visible text from any given URL.
  • analyze_sentiment: Analyzes the sentiment of a given text using HuggingFace Transformers.
  • generate_text: Generates text based on a prompt using HuggingFace Transformers.

Requirements

  • Python 3.8+
  • Install dependencies:
    • pip install -r requirements.txt
    • (If not present, create a requirements.txt with: requests beautifulsoup4 transformers torch mcp)

Usage

  1. Activate your virtual environment
    • Windows PowerShell: ./mcp-env/Scripts/Activate.ps1
  2. Run the server
    • python mcp-env/webscraper_server.py
  3. Connect via MCP client or VS Code MCP extension
    • Use the MCP sidebar to call tools interactively.

Example Tools

  • scrape_webpage(url): Returns the page title and first 1000 characters of visible text.
  • analyze_sentiment(text): Returns sentiment label and score.
  • generate_text(prompt, max_length=100): Returns generated text for a prompt.

Notes

  • Some websites (like YouTube or Flipkart) may restrict scraping or require custom headers.
  • For dynamic content (e.g., JavaScript-heavy sites), consider using Selenium or Playwright.

License

MIT