decodo-mcp-server

Decodo/decodo-mcp-server

3.4

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

The Decodo MCP Server is a Model Context Protocol server that connects LLMs and applications to Decodo's platform, facilitating integration and streamlining access to Decodo's tools and capabilities.

The Decodo MCP Server is designed to bridge the gap between large language models (LLMs) and applications with Decodo's platform. By leveraging the Model Context Protocol (MCP), this server enables seamless integration with MCP-compatible clients, providing users with easy access to Decodo's advanced web scraping and data retrieval services. The server supports geographic flexibility, allowing users to access content without regional restrictions, and enhances privacy by maintaining anonymity during data collection. With reliable scraping techniques, the server ensures that users can gather data without detection or blocks. The Decodo MCP Server is compatible with popular MCP clients like Claude Desktop, Cursor, and Windsurf, making it a versatile tool for developers and data analysts.

Features

  • Easy web data access: Simplified retrieval of information from websites and online sources.
  • Geographic flexibility: Access content regardless of regional restrictions.
  • Enhanced privacy: Browse and collect data while maintaining anonymity.
  • Reliable scraping: Advanced techniques to avoid detection and blocks.
  • Simple integration: Seamless setup with popular MCP clients like Claude Desktop, Cursor, and Windsurf.

Usages

usage with Claude Desktop

{
  "mcpServers": {
    "decodo-mcp": {
      "command": "node",
      "args": ["/Users/your.user/projects/decodo-mcp/build/index.js"],
      "env": {
        "SCRAPER_API_USERNAME": "your_username",
        "SCRAPER_API_PASSWORD": "your_password"
      }
    }
  }
}

Tools

  1. scrape_as_markdown

    Scrapes any target URL, expects a URL to be given via prompt. Returns results in Markdown.

  2. google_search_parsed

    Scrapes Google Search for a given query, and returns parsed results.

  3. amazon_search_parsed

    Scrapes Amazon Search for a given query, and returns parsed results.