ScrapeGraphAI-scrapegraph-mcp — Claude Code MCP server: features
Connect Claude Code to ScrapeGraph API for web search, data extraction, and page crawling. A ScrapeGraph API key is required.
claude mcp add --transport http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcpWhat ScrapeGraphAI-scrapegraph-mcp does
The server gives an MCP client tools for web tasks. scrape returns page content in a chosen format, extract gathers information from a URL based on a prompt, and search finds pages. For multi-page jobs, use the asynchronous crawl_start, crawl_get_status, crawl_stop, and crawl_resume tools.
It can also create or extend a JSON Schema from a prompt and manage scheduled monitors. The credits and history tools expose account credits and request history. This service relies on ScrapeGraph API, so requests need a ScrapeGraph API key.
The server targets ScrapeGraph API v2. Set SGAI_API_KEY or provide the key through MCP configuration. Claude Code connects over HTTP; Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, and Zed are also listed as supported platforms.
What it helps with
- search for pages matching a query
- extract requested fields from a website
- crawl a site and collect page content
- return scraped content as Markdown or HTML
- track changes with scheduled monitors
Example prompts for the agent
- Find pages about recent Python releases and summarize what they say.
- Extract product names and prices from this page.
- Crawl the site and collect its pages as Markdown.
How to install ScrapeGraphAI-scrapegraph-mcp
Platform CLI: remote server
claude mcp add --transport http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcpPlatform CLI: remote server
codex mcp add scrapegraphai-scrapegraph-mcp --url https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcpConfig file
{
"mcpServers": {
"scrapegraphai-scrapegraph-mcp": {
"url": "https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp"
}
}
}Config file
{
"servers": {
"scrapegraphai-scrapegraph-mcp": {
"type": "http",
"url": "https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about ScrapeGraphAI-scrapegraph-mcp
How do I install ScrapeGraphAI-scrapegraph-mcp in Claude Code?
Run claude mcp add --transport http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp. Then configure a ScrapeGraph API key for requests.
What does ScrapeGraphAI-scrapegraph-mcp do?
It exposes ScrapeGraph tools through MCP for web search, data extraction, crawling, and scheduled monitors. Scraped results can use formats such as Markdown or HTML.
What credentials does the server need?
It requires a ScrapeGraph API key. Provide it through SGAI_API_KEY or the MCP scrapegraphApiKey setting.
