Add to Docker Desktop
Version 4.43 or later needs to be installed to add the server automatically
Use cases
About
ScrapeGraph MCP Server
ScapeGraph MCP Server.
Characteristics
| Attribute | Details |
|---|---|
| Docker Image | mcp/scrapegraph |
| Author | ScrapeGraphAI |
| Repository | https://github.com/ScrapeGraphAI/scrapegraph-mcp |
| Dockerfile | https://github.com/ScrapeGraphAI/scrapegraph-mcp/blob/main/Dockerfile |
| Docker Image built by | Docker Inc. |
| Docker Scout Health Score | |
| Verify Signature | COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/scrapegraph --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub |
| Licence | MIT License |
Available Tools (5)
| Tools provided by this Server | Short Description |
|---|---|
markdownify | Convert a webpage into clean, formatted markdown. |
searchscraper | Perform AI-powered web searches with structured results. |
smartcrawler_fetch_results | Fetch the results of a SmartCrawler operation. |
smartcrawler_initiate | Initiate a SmartCrawler request for intelligent multi-page web crawling. |
smartscraper | Extract structured data from a webpage using AI. |
Tools Details
Tool: markdownify
Convert a webpage into clean, formatted markdown.
| Parameters | Type | Description |
|---|---|---|
website_url | string | URL of the webpage to convert |
Tool: searchscraper
Perform AI-powered web searches with structured results.
| Parameters | Type | Description |
|---|---|---|
user_prompt | string | Search query or instructions |
num_results | integeroptional | Number of websites to search (optional, default: 3 websites = 30 credits) |
number_of_scrolls | integeroptional | Number of infinite scrolls to perform on each website (optional) |
Tool: smartcrawler_fetch_results
Fetch the results of a SmartCrawler operation.
| Parameters | Type | Description |
|---|---|---|
request_id | string | The request ID returned by smartcrawler_initiate |
Tool: smartcrawler_initiate
Initiate a SmartCrawler request for intelligent multi-page web crawling.
SmartCrawler supports two modes:
- AI Extraction Mode (10 credits per page): Extracts structured data based on your prompt
- Markdown Conversion Mode (2 credits per page): Converts pages to clean markdown
| Parameters | Type | Description |
|---|---|---|
url | string | Starting URL to crawl |
depth | integeroptional | Maximum link traversal depth (optional) |
extraction_mode | stringoptional | "ai" for AI extraction or "markdown" for markdown conversion (default: "ai") |
max_pages | integeroptional | Maximum number of pages to crawl (optional) |
prompt | stringoptional | AI prompt for data extraction (required for AI mode) |
same_domain_only | booleanoptional | Whether to crawl only within the same domain (optional) |
Tool: smartscraper
Extract structured data from a webpage using AI.
| Parameters | Type | Description |
|---|---|---|
user_prompt | string | Instructions for what data to extract |
website_url | string | URL of the webpage to scrape |
markdown_only | booleanoptional | Whether to return only markdown content without AI processing (optional) |
number_of_scrolls | integeroptional | Number of infinite scrolls to perform (optional) |
Use this MCP Server
{
"mcpServers": {
"scrapegraph": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SGAI_API_KEY",
"mcp/scrapegraph"
],
"env": {
"SGAI_API_KEY": "YOUR_SGAI_API_KEY"
}
}
}
}
Manual installation
You can install the MCP server using:
Installation for