Scrapegraph Mcp

scrapegraphai/scrapegraph-mcp

Plugs Claude or Cursor directly into the ScrapeGraph AI API for production web scraping. You get tools for single-page scraping in multiple formats (markdown, HTML, screenshots), structured extraction with custom prompts and schemas, web search with country and time filters, multi-page crawling with pause and resume, and scheduled monitoring jobs. It targets the v2 API, handles crawl status polling, and exposes credit balance and request history endpoints. Useful when you need AI-powered extraction at scale without writing scraper code yourself. Ships with Smithery support and a hosted remote server option if you want zero local setup.

GitHub stars: 82
tools: 8
auth: Secret needed
transport: STDIO
env var: 1
last updated: Feb 7, 2026

View on GitHub

Tools

8 tools

Public tool metadata for what this MCP can expose to an agent.

markdownifyConvert a webpage into clean, formatted markdown. This tool fetches any webpage and converts its content into clean, readable markdown format. Useful for extracting content from documentation, articles, and web pages for further processing. Costs 2 credits per page. Read-only...1 params

Convert a webpage into clean, formatted markdown. This tool fetches any webpage and converts its content into clean, readable markdown format. Useful for extracting content from documentation, articles, and web pages for further processing. Costs 2 credits per page. Read-only...

Parameters* required

website_urlstring

smartscraperExtract structured data from a webpage, HTML, or markdown using AI-powered extraction. This tool uses advanced AI to understand your natural language prompt and extract specific structured data from web content. Supports three input modes: URL scraping. Ideal for extracting pr...9 params

Extract structured data from a webpage, HTML, or markdown using AI-powered extraction. This tool uses advanced AI to understand your natural language prompt and extract specific structured data from web content. Supports three input modes: URL scraping. Ideal for extracting pr...

Parameters* required

number_of_scrollsvalue

output_schemavalue

render_heavy_jsvalue

stealthvalue

total_pagesvalue

user_promptstring

website_htmlvalue

website_markdownvalue

website_urlvalue

searchscraperPerform AI-powered web searches with structured data extraction. This tool searches the web based on your query and uses AI to extract structured information from the search results. Ideal for research, competitive analysis, and gathering information from multiple sources. Eac...3 params

Perform AI-powered web searches with structured data extraction. This tool searches the web based on your query and uses AI to extract structured information from the search results. Ideal for research, competitive analysis, and gathering information from multiple sources. Eac...

Parameters* required

num_resultsvalue

number_of_scrollsvalue

user_promptstring

smartcrawler_initiateInitiate an asynchronous multi-page web crawling operation with AI extraction or markdown conversion. This tool starts an intelligent crawler that discovers and processes multiple pages from a starting URL. Choose between AI Extraction Mode (10 credits/page) for structured dat...6 params

Initiate an asynchronous multi-page web crawling operation with AI extraction or markdown conversion. This tool starts an intelligent crawler that discovers and processes multiple pages from a starting URL. Choose between AI Extraction Mode (10 credits/page) for structured dat...

Parameters* required

depthvalue

extraction_modestring

default: ai

max_pagesvalue

promptvalue

same_domain_onlyvalue

urlstring

smartcrawler_fetch_resultsRetrieve the results of an asynchronous SmartCrawler operation. This tool fetches the results from a previously initiated crawling operation using the request_id. The crawl request processes asynchronously in the background. Keep polling this endpoint until the status field in...1 params

Retrieve the results of an asynchronous SmartCrawler operation. This tool fetches the results from a previously initiated crawling operation using the request_id. The crawl request processes asynchronously in the background. Keep polling this endpoint until the status field in...

Parameters* required

request_idstring

scrapeFetch raw page content from any URL with optional JavaScript rendering. This tool performs basic web scraping to retrieve the raw HTML content of a webpage. Optionally enable JavaScript rendering for Single Page Applications (SPAs) and sites with heavy client-side rendering. L...2 params

Fetch raw page content from any URL with optional JavaScript rendering. This tool performs basic web scraping to retrieve the raw HTML content of a webpage. Optionally enable JavaScript rendering for Single Page Applications (SPAs) and sites with heavy client-side rendering. L...

Parameters* required

render_heavy_jsvalue

website_urlstring

sitemapExtract and discover the complete sitemap structure of any website. This tool automatically discovers all accessible URLs and pages within a website, providing a comprehensive map of the site's structure. Useful for understanding site architecture before crawling or for discov...1 params

Extract and discover the complete sitemap structure of any website. This tool automatically discovers all accessible URLs and pages within a website, providing a comprehensive map of the site's structure. Useful for understanding site architecture before crawling or for discov...

Parameters* required

website_urlstring

agentic_scrapperExecute complex multi-step web scraping workflows with AI-powered automation. This tool runs an intelligent agent that can navigate websites, interact with forms and buttons, follow multi-step workflows, and extract structured data. Ideal for complex scraping scenarios requiri...7 params

Execute complex multi-step web scraping workflows with AI-powered automation. This tool runs an intelligent agent that can navigate websites, interact with forms and buttons, follow multi-step workflows, and extract structured data. Ideal for complex scraping scenarios requiri...

Parameters* required

ai_extractionvalue

output_schemavalue

persistent_sessionvalue

stepsvalue

timeout_secondsvalue

urlstring

user_promptvalue

Configuration

SGAI_API_KEYsecret

Your ScapeGraph API key (optional - can also be set via MCP config)

Readme

ScrapeGraph MCP Server

ScrapegraphAI Logo

A production-ready Model Context Protocol (MCP) server that provides seamless integration with the ScrapeGraph AI API. This server enables language models to leverage advanced AI-powered web scraping capabilities with enterprise-grade reliability.

View the full README on GitHub

Details

Repository: github.com/scrapegraphai/scrapegraph-mcp
Categories: Search & Web Crawling, Data & Analytics
Package: scrapegraph-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active

Related Search & Web Crawling MCP servers

View all

Endnote Mcpgokmengokhan/endnote-mcpSearch, cite, and read PDFs from your EndNote library in Claude Desktop59stars

Mcp Apple Musiccifero74/mcp-apple-musicApple Music MCP server — search catalog, manage playlists, and access your library via Claude.45stars

Mcp Serverdecodo/mcp-serverEnable your AI agents to scrape and parse web content dynamically, including geo-restricted sites0stars

OmniClip RAGmsjsc001/omniclip-ragRead-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.37stars

Seekstoneshaqmughal/seekstoneFilesystem-direct Obsidian MCP server — search and edit your vault with low context-tax.35stars

PageMapretio-ai/retio-pagemapStructured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy32stars

Scrapegraph Mcp

Tools

Configuration

Readme

ScrapeGraph MCP Server

Table of Contents

Details

More from scrapegraphai

Related Search & Web Crawling MCP servers