Prysm MCP Server

🚀 Prysm MCP

Prysm MCP is a powerful tool designed for AI assistants. It aims to enhance their scraping capabilities through the Model Context Protocol. It supports multiple browser engines and provides efficient web scraping and parsing functions via Puppeteer.

🚀 Quick Start

📦 Installation

# Global installation
npm install -g @pinkpixel/prysm-mcp

# Local development environment installation
npm install @pinkpixel/prysm-mcp

Integration Guide

Here are several common integration methods:

1. Standalone operation:

   # Run with default configuration
   prysm-mcp
   
   # Custom output directory
   PRYSM_OUTPUT_DIR=./output PRYSM_IMAGE_OUTPUT_DIR=./output/images prysm-mcp
   

2. Run via npx:

   # Default mode
   npx @pinkpixel/prysm-mcp
   
   # Custom configuration
   PRYSM_OUTPUT_DIR=./custom-output PRYSM_IMAGE_OUTPUT_DIR=./custom-output/images npx @pinkpixel/prysm-mcp
   

3. Via MCP configuration file: Create or edit the .cursor/mcp.json file in your workspace and add the following content:

   {
     "mcpServers": {
       "prysm-scraper": {
         "command": "npx",
         "args": ["-y", "@pinkpixel/prysm-mcp"],
         "env": {
           "PRYSM_OUTPUT_DIR": "${workspaceFolder}/scrape_results",
           "PRYSM_IMAGE_OUTPUT_DIR": "${workspaceFolder}/scrape_results/images"
         }
       }
     }
   }
   

✨ Features

• Multi-browser support: Prysm MCP supports mainstream browser engines such as Chromium, Firefox, and WebKit.
• High configurability: Users can customize scraping behavior according to their needs to meet requirements in different scenarios.
• Efficient performance: It has built - in optimization algorithms to ensure efficient operation in complex tasks.

📚 Documentation

Scraping Tools

• prysm-mcp: Responsible for handling web scraping and parsing tasks.
• formatResult: Used to format and save scraping results.

Configuration Parameters

Output Directory Settings

• The default output path is ~/prysm-mcp/output/. Users can customize it in the following ways:

  • Environment variables:

    # On Linux/macOS systems
    export PRYSM_OUTPUT_DIR="/path/to/custom/directory"
    export PRYSM_IMAGE_OUTPUT_DIR="/path/to/custom/image/directory"
    
    # In Windows Command Prompt
    set PRYSM_OUTPUT_DIR=C:\path\to\custom\directory
    set PRYSM_IMAGE_OUTPUT_DIR=C:\path\to\custom\image\directory
    
    # In PowerShell
    $env:PRYSM_OUTPUT_DIR="C:\path\to\custom\directory"
    $env:PRYSM_IMAGE_OUTPUT_DIR="C:\path\to\custom\image\directory"
    

  • Directly specify the path:

    # Save to a specified file
    Format the scraped data as markdown and save to file:/path/to/output.md
    
    # Specify the output directory
    PRYSM_OUTPUT_DIR=/tmp prysm-mcp
    

Path Handling Rules

• Absolute path: Use the full file path directly.
• Relative path: Resolve based on the current working directory.
• Special value file: Used to specify output to a specific file.

🔧 Technical Details

Operating Environment

• Node.js: The version should be 14.0 or higher.
• Puppeteer: It depends on the Puppeteer library for browser control.

Debugging and Logging

# Start debug mode
DEBUG=prysm-mcp prysm-mcp

# View help information
prysm-mcp --help

📄 License

Prysm MCP is licensed under the MIT License, which allows users to freely use, modify, and distribute the code. For detailed license content, please refer to the LICENSE file in the project repository.

Project Team

• Development Team: Pink Pixel team.
• Contact Information: For feedback or cooperation, please visit https://github.com/pinkpixel.

Thank you for choosing Prysm MCP. We hope it can provide efficient support for your project!