# ScrapeGraphAI-scrapegraph-mcp

Connect Claude Code to ScrapeGraph API for web search, data extraction, and page crawling. A ScrapeGraph API key is required.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 117
- Author: ScrapeGraphAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ScrapeGraphAI/scrapegraph-mcp
- Updated: 2026-07-17
- HTML: https://affpapa.org/en/nevibecode/mcp/scrapegraphai-scrapegraph-mcp

## What it 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.

## Requirements
- Remote server: `https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add scrapegraphai-scrapegraph-mcp --url https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapegraphai-scrapegraph-mcp": {
            "url": "https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapegraphai-scrapegraph-mcp": {
            "type": "http",
            "url": "https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http scrapegraphai-scrapegraph-mcp https://server.smithery.ai/@ScrapeGraphAI/scrapegraph-mcp/mcp
```

## When to use it
- 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
- 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.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md