Web Content Pick

Provides a backend to extract structured web content using CSS selectors with recursive crawling and retries.

javascript

1

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kilicmu-mcp-web-content-pick": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-web-content-pick"
      ]
    }
  }
}

You can use this MCP server to automate extraction of structured content from web pages. It leverages customizable selectors and recursive crawling to produce clean, hierarchical output that you can feed into your data workflows or content pipelines.

How to use

Install the MCP server tooling and run it via an MCP client to pull structured content from any web page. You configure the server, then request extractions with your client to target specific page sections, apply depth-controlled crawling, and receive consistent results.

How to install

Prerequisites you need before installing: Node.js and npm installed on your system.

# Install Node.js and npm if needed from https://nodejs.org/
# Then install the MCP server tool globally
npm install -g mcp-web-content-pick

Additional notes

Configure your MCP client to use the stdio-based MCP server entry that runs the web content extractor. The command uses npx to execute the web content pick tool with an automatic-yes flag so you can integrate it into scripts or automation.

{
  "mcpServers": {
    "web_content_search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-web-content-pick"
      ]
    }
  }
}

Available tools

web_content_pick

Extracts structured content from web pages using customizable CSS selectors, with recursive crawling, automatic retries, and a clean hierarchical output.