ScrapeGraph MCP Server

Official

MIT License

Overview InspectNew Endpoints Schema Related Servers Reviews Score

smartscraper

Extract structured data from webpages using AI by specifying user prompts and URLs. Ideal for automating data retrieval and transforming web content into markdown or processed formats.

Instructions

Extract structured data from a webpage using AI.

Args:
    user_prompt: Instructions for what data to extract
    website_url: URL of the webpage to scrape
    number_of_scrolls: Number of infinite scrolls to perform (optional)
    markdown_only: Whether to return only markdown content without AI processing (optional)

Returns:
    Dictionary containing the extracted data or markdown content

Input Schema

Name	Required	Description	Default
`markdown_only`	No
`number_of_scrolls`	No
`user_prompt`	Yes
`website_url`	Yes

Input Schema (JSON Schema)

{
  "properties": {
    "markdown_only": {
      "default": null,
      "title": "Markdown Only",
      "type": "boolean"
    },
    "number_of_scrolls": {
      "default": null,
      "title": "Number Of Scrolls",
      "type": "integer"
    },
    "user_prompt": {
      "title": "User Prompt",
      "type": "string"
    },
    "website_url": {
      "title": "Website Url",
      "type": "string"
    }
  },
  "required": [
    "user_prompt",
    "website_url"
  ],
  "title": "smartscraperArguments",
  "type": "object"
}

This server cannot be installed

Other Tools from ScrapeGraph MCP Server

Related Tools

firecrawl_extract_process
@spences10/mcp-omnisearch
extract-structured-data
@kxkaloo/mcp
extract
@Dumpling-AI/mcp-server-dumplingai
extract_structured_data
@hyperbrowserai/mcp
extract-structured-data
@Scrapezy/mcp
extract-data
@codyde/mcp-firecrawl-tool

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ScrapeGraphAI/scrapegraph-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server