softengineware/mcp-scrape

3.2

If you are the rightful owner of mcp-scrape 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.

MCP-Scrape is a military-grade web scraping MCP server designed for precision, reliability, adaptability, and no failure.

Tools

Functions exposed to the LLM to take actions

scrape_url

Single URL extraction with multiple fallback strategies.

crawl_site

Full site crawling with intelligent link following.

search_web

Advanced Google search with structured queries.

extract_data

LLM-powered data extraction with schemas.

screenshot

Visual capture of any webpage.

interact

Browser automation for dynamic content.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources

Author

softengineware

Claim Ownership

Verify you have write access to the repository

Repository

https://github.com/softengineware/mcp-scrape

License

MIT License

Last publish date

2025-05-26

Last update date

2025-05-27

Server configs

in claude desktop

{
  "mcpServers": {
    "scrape": {
      "command": "docker",
      "args": [
        "run",
        "--env-file",
        ".env",
        "-p",
        "8080:8080",
        "mcp/scrape"
      ]
    }
  }
}

via npx in vs code

{
  "mcp": {
    "servers": {
      "scrape": {
        "command": "npx",
        "args": [
          "-y",
          "@modelcontextprotocol/server-scrape"
        ]
      }
    }
  }
}

in vs code

{
  "mcp": {
    "servers": {
      "scrape": {
        "command": "docker",
        "args": [
          "run",
          "--env-file",
          ".env",
          "-p",
          "8080:8080",
          "mcp/scrape"
        ]
      }
    }
  }
}