# Scrapling MCP Server

Web scraping MCP server with stealth browsers, JavaScript rendering, and Cloudflare bypass. Extracts clean Markdown and structured page data for AI agents.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 89433
- Author: D4Vinci
- License: BSD-3-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/D4Vinci/Scrapling
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server

## What it does

This server connects the Scrapling framework to coding environments like Claude Code, Codex, and Cursor. It equips your assistant with stealth HTTP requests, headless browser control, and parsing via CSS selectors or XPath. Background challenge solving handles Cloudflare Turnstile and interstitial screens automatically.

The framework supports persistent sessions, proxy rotation, and exports to clean Markdown or JSON. Running the server requires `uvx scrapling`, so having `uv` and Python on your system is mandatory. Without `uvx`, the agent cannot launch the runtime process.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add scrapling -- uvx scrapling
```
uvx runs the command named after the package; if the README names another one, use uvx --from scrapling <command>

### Codex

**Platform CLI**
```bash
codex mcp add scrapling-mcp-server -- uvx scrapling
```
uvx runs the command named after the package; if the README names another one, use uvx --from scrapling <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapling-mcp-server": {
            "command": "uvx",
            "args": [
                "scrapling"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from scrapling <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapling-mcp-server": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "scrapling"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from scrapling <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add scrapling-mcp-server uvx scrapling
```
uvx runs the command named after the package; if the README names another one, use uvx --from scrapling <command>

## When to use it
- bypass Cloudflare Turnstile screens when reading web targets
- render dynamic JavaScript pages with a stealth browser
- convert HTML page contents into clean Markdown for context
- extract elements using CSS selectors or XPath queries

## Example prompts
- Scrape quotes from `https://quotes.toscrape.com/` using CSS selectors
- Fetch the documentation behind Cloudflare and return the content as Markdown
- Inspect the target table layout and parse the data into JSON

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989

From the same set: [d4vinci/scrapling](https://affpapa.org/en/nevibecode/by/d4vinci/scrapling.md) — 2 cards

---
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