# mcp

Scrapfly connects an AI assistant to live webpages, extracts structured data as JSON, and captures page screenshots.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 14
- Author: scrapfly
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/scrapfly/scrapfly-mcp
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/scrapfly-mcp

## What it does

The Scrapfly server gives an AI assistant access to web content through MCP. It can fetch page data such as prices, listings, and news, turn complex pages into structured JSON, and capture a whole page or a specific element.

It also handles CAPTCHAs, proxies, JavaScript rendering, and request limits. That matters on sites with anti-bot measures: the server takes care of those steps. In Claude Code, add it through the CLI; the command starts the `scrapfly-mcp` package with `npx`.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mcp -- npx -y scrapfly-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add scrapfly-mcp -- npx -y scrapfly-mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapfly-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "scrapfly-mcp"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapfly-mcp": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "scrapfly-mcp"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add scrapfly-mcp npx -y scrapfly-mcp
```

## When to use it
- collect current prices from webpages
- extract page content into structured JSON
- gather news page content
- capture a page or a specific element
- scrape sites that present CAPTCHAs

## Example prompts
- Collect the current prices from this page and return them as JSON.
- Extract the listings from this site into a structured list.
- Capture this page and describe what it shows.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74559
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433

## Other versions with the same name
- [mcp · kubeshark](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — ★ 12109
- [mcp · butterbase-ai](https://affpapa.org/en/nevibecode/mcp/butterbase-ai-mcp.md) — ★ 3031
- [mcp · medplum](https://affpapa.org/en/nevibecode/mcp/mcp.md) — ★ 2760
- [mcp · sceneview](https://affpapa.org/en/nevibecode/mcp/sceneview-mcp.md) — ★ 1348
- [mcp · buoy-gg](https://affpapa.org/en/nevibecode/mcp/buoy-gg-mcp.md) — ★ 691

---
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