Smithery Scrapegraphai Scrapegraph MCP Server

Scrape and extract data from websites using AI-powered parsing with enterprise reliability. Integrates ScrapeGraph AI's API into Claude, Cursor, and other LLMs via MCP for markdown conversion, structured extraction, web search, and multi-page crawling.

ai.smithery/ScrapeGraphAI-scrapegraph-mcp

Example prompts for Smithery Scrapegraphai Scrapegraph

Paste any of these into Agent Studio after connecting Smithery Scrapegraphai Scrapegraph.

Convert https://example.com to markdown and extract all headings

Extract product names and prices from this e-commerce page using a JSON schema

Search for the latest AI news and summarize the top 5 results

Crawl all pages under https://docs.example.com and extract code examples

Excerpted from the project's README — boilerplate sections (license, changelog, contributing) omitted for clarity.

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.

Key Features
Quick Start
Available Tools
Setup Instructions
Remote Server Usage
Local Usage
Google ADK Integration
Example Use Cases
Error Handling
Common Issues
Development
Contributing
Documentation
Technology Stack
License

API v2

This MCP server targets ScrapeGraph API v2 (https://v2-api.scrapegraphai.com/api), aligned 1:1 with scrapegraph-py PR #84. Auth uses the SGAI-APIKEY header. Environment variables mirror the Python SDK:

SGAI_API_URL — override the base URL (default https://v2-api.scrapegraphai.com/api)
SGAI_TIMEOUT — request timeout in seconds (default 120)
SGAI_API_KEY — API key (can also be passed via MCP scrapegraphApiKey or X-API-Key header)

Legacy aliases (still honored): SCRAPEGRAPH_API_BASE_URL for SGAI_API_URL, SGAI_TIMEOUT_S for SGAI_TIMEOUT.

Key Features

Scrape & extract: scrape (POST /scrape, multi-format), extract (POST /extract, URL + prompt)
Search: search (POST /search; num_results clamped 3–20)
Crawl: Async multi-page crawl with crawl_start / crawl_get_status / crawl_stop / crawl_resume
Schema: schema (POST /schema) — generate or augment a JSON Schema from a prompt
Monitors: Scheduled jobs via monitor_create, monitor_list, monitor_get, pause/resume/delete, monitor_activity (paginated tick history)
Account: credits, history
Easy integration: Claude Desktop, Cursor, Smithery, HTTP transport
Developer docs: .agent/ folder

Migration: v2 → v3

v3 renames every MCP tool that diverged from the v2 API docs. Hard rename, no aliases.

v2 (old)	v3 (new)
`smartscraper`	`extract`
`searchscraper`	`search`
`smartcrawler_initiate`	`crawl_start`
`smartcrawler_fetch_results`	`crawl_get_status`
`sgai_history`	`history`
`generate_schema`	`schema`
`markdownify`	removed — use `scrape` with `output_format="markdown"`

Quick Start

1. Get Your API Key

2. Install with Smithery (Recommended)

npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude

3. Start Using

Ask Claude or Cursor:

"Convert https://scrapegraphai.com to markdown"
"Extract all product prices from this e-commerce page"
"Research the latest AI developments and summarize findings"

That's it! The server is now available to your AI assistant.

Smithery Scrapegraphai Scrapegraph MCP server — FAQ

Common questions about connecting and running Smithery Scrapegraphai Scrapegraph.

What can I scrape with this MCP server?

You can scrape websites in multiple formats (markdown, HTML, screenshots, links, images, summaries), extract structured data with AI-powered prompts, perform web searches, crawl multi-page sites, and generate JSON schemas. The README lists 14+ tools covering scraping, extraction, search, crawling, and monitoring.

How do I set up authentication?

Sign up at the ScrapeGraph Dashboard to get an API key, then set it via the `SGAI_API_KEY` environment variable or pass it in your MCP client config (Claude Desktop, Cursor, or Smithery). The server also accepts `X-API-Key` headers for remote connections.

What's the difference between scrape and extract?

The `scrape` tool converts a URL to a specified format (markdown, HTML, etc.) without a prompt. The `extract` tool requires both a URL and a user prompt to intelligently pull structured data matching your needs.

Can I run this locally or only remotely?

Both. You can install locally via pip (Python 3.13+) and run `scrapegraph-mcp` directly, or connect to the hosted remote server at `https://scrapegraph-mcp.onrender.com/mcp`. Local setup requires setting `SGAI_API_KEY` as an environment variable.

Is there a free tier or pricing information?

The README does not document pricing or free tier details. You'll need to check the ScrapeGraph Dashboard or website for credit costs and billing. The server includes a `credits` tool to check your account balance.