@scrapezy/mcp

Provides a MCP server that lets AI models extract structured data from websites using the extract_structured_data tool.

javascript

13

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": {
    "scrapezy-mcp": {
      "command": "npx",
      "args": [
        "@scrapezy/mcp",
        "--api-key",
        "YOUR_API_KEY"
      ],
      "env": {
        "SCRAPEZY_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run a MCP server that enables AI models to extract structured data from websites by calling a dedicated tool. It exposes a simple CLI interface and can be configured to work with Claude Desktop or other MCP clients, making it easy to plug your data extraction workflow into your AI prompts.

How to use

To use this MCP server, provide your API key and start the server from your client. Your client will send prompts and URLs to the server, which returns structured data extracted from the target page according to your instructions. Common usage involves starting the server with your API key and issuing prompts like: extract data from a specific page, asking for product details, contact information, or other structured data you need to collect.

How to install

Prerequisites: Node.js and npm must be installed on your machine.

Manual installation steps you can follow:

npm install -g @scrapezy/mcp

Additional setup for API access and client configurations

Set your API key in the environment or pass it as a flag when starting the MCP server, then configure your MCP client to connect to the local stdio endpoint.

Environment variable method example:

export SCRAPEZY_API_KEY=your_api_key
npx @scrapezy/mcp

Configuring Claude Desktop or other MCP clients

If you use Claude Desktop, add a server configuration that runs the MCP server with your API key. The following example shows the JSON you would place in the Claude desktop config to launch the MCP server.

{
  "mcpServers": {
    "scrapezy": {
      "command": "npx @scrapezy/mcp --api-key=your_api_key"
    }
  }
}

Available tools

extract_structured_data

Extract structured data from a website by providing a URL and a prompt that clearly describes the data you want to extract. The tool returns the structured data based on your prompt.