UseScraper

MCP server for the useScraper API. This is a server that scrapes a URL to text or markdown

javascript

4

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks 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": {
    "tanevanwifferen-usescraper-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/usescraper-server/build/index.js"
      ],
      "env": {
        "USESCRAPER_API_KEY": "your-api-key-here"
      }
    }
  }
}

UseScraper MCP Server gives you web scraping capabilities through the UseScraper API. It exposes a single tool, scrape, that lets you extract content from web pages in formats you choose, making it easy to automate data collection within your MCP workflow.

How to use

You will run the scrape tool through the MCP client connected to this server. Provide the target page URL and choose a format for the scraped content. Optional features include enabling a proxy to bypass bot detection and specifying data to extract. The key idea is: give the URL you want to scrape, pick a destination format (text, html, or markdown), and let the tool return the extracted content for your downstream tasks.

How to install

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

Install via Smithery to integrate automatic client setup for Claude Desktop:

npm -y @smithery/cli install usescraper-server --client claude

How to install

Manual installation steps you can perform locally to run the UseScraper MCP server:

Clone the repository and install dependencies:

git clone https://github.com/your-repo/usescraper-server.git
cd usescraper-server
npm install

How to install

Build the server after installing dependencies:

npm run build

Configuration

To use with Claude Desktop, place a MCP config in the Claude Desktop config path and specify how to start the server and supply your API key.

Configuration

Example Claude Desktop MCP configuration (assumes you replace the path to the built server and insert your API key):

Configuration

{
  "mcpServers": {
    "usescraper-server": {
      "command": "node",
      "args": ["/path/to/usescraper-server/build/index.js"],
      "env": {
        "USESCRAPER_API_KEY": "your-api-key-here"
      }
    }
  }
}

Usage example

Once configured, you can invoke the scrape tool with your target URL and desired format. Example usage through the MCP client:

{
  "name": "scrape",
  "arguments": {
    "url": "https://example.com",
    "format": "markdown"
  }
}

Available tools

scrape

Extract content from a webpage. Required parameter is url. Optional parameters include format (text, html, markdown), advanced_proxy to use a proxy, and extract_object to specify data to extract.