> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/D4Vinci/Scrapling/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Model Context Protocol server for AI-powered web scraping

Scrapling provides a Model Context Protocol (MCP) server that enables AI assistants to perform web scraping operations. The server exposes Scrapling's fetching capabilities as MCP tools.

## Overview

The Scrapling MCP server allows AI models to:

* Fetch web pages with stealth HTTP requests
* Extract content using CSS selectors
* Handle JavaScript-heavy sites with browser automation
* Bypass Cloudflare and other protections
* Process single or multiple URLs concurrently
* Return structured data in Markdown, HTML, or text format

## Quick Start

### Start the Server

```bash theme={null}
scrapling mcp
```

This starts the server in stdio transport mode (default).

### HTTP Transport

For network access, use streamable-http transport:

```bash theme={null}
scrapling mcp --http --host 0.0.0.0 --port 8000
```

## Server Configuration

The MCP server configuration is defined in `server.json`:

```json theme={null}
{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.D4Vinci/Scrapling",
  "title": "Scrapling MCP Server",
  "description": "Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.",
  "version": "0.4.1"
}
```

## Available Tools

The MCP server exposes six main tools:

<CardGroup cols={2}>
  <Card title="get" icon="arrow-down">
    Make HTTP GET requests with stealth features
  </Card>

  <Card title="bulk_get" icon="list">
    Fetch multiple URLs concurrently with GET requests
  </Card>

  <Card title="fetch" icon="browser">
    Use Playwright for JavaScript-heavy sites
  </Card>

  <Card title="bulk_fetch" icon="browsers">
    Fetch multiple URLs with browser automation
  </Card>

  <Card title="stealthy_fetch" icon="shield">
    Advanced stealth with Cloudflare bypass
  </Card>

  <Card title="bulk_stealthy_fetch" icon="shields">
    Stealthy fetching for multiple URLs
  </Card>
</CardGroup>

## Transport Modes

### Stdio Transport (Default)

Used for local AI assistants:

```bash theme={null}
scrapling mcp
```

* Standard input/output communication
* Best for Claude Desktop, Cline, and other local clients
* No network configuration needed

### HTTP Transport

Used for network-accessible services:

```bash theme={null}
scrapling mcp --http --host 0.0.0.0 --port 8000
```

* Streamable HTTP transport
* Accessible over network
* Configurable host and port

## Response Format

All tools return a structured `ResponseModel`:

```python theme={null}
{
  "status": 200,
  "content": ["Extracted content..."],
  "url": "https://example.com"
}
```

<ResponseField name="status" type="integer">
  HTTP status code from the website
</ResponseField>

<ResponseField name="content" type="array[string]">
  Extracted content as Markdown, HTML, or text
</ResponseField>

<ResponseField name="url" type="string">
  The URL that was requested
</ResponseField>

## Installation Methods

### PyPI (Recommended)

```bash theme={null}
uvx scrapling mcp
```

Or with pip:

```bash theme={null}
pip install scrapling
scrapling mcp
```

### Docker (OCI)

```bash theme={null}
docker pull ghcr.io/d4vinci/scrapling
docker run ghcr.io/d4vinci/scrapling mcp
```

## Use Cases

<AccordionGroup>
  <Accordion title="AI-powered web research">
    Enable AI assistants to gather information from websites, extract articles, and process web content.
  </Accordion>

  <Accordion title="Automated data collection">
    Let AI models collect data from multiple sources concurrently with bulk operations.
  </Accordion>

  <Accordion title="Content analysis">
    Extract and analyze web content using CSS selectors for targeted data extraction.
  </Accordion>

  <Accordion title="Protected site access">
    Use stealthy fetching to access Cloudflare-protected sites through AI workflows.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Setup Guide" icon="gear" href="/ai/setup">
    Configure MCP server for your AI client
  </Card>

  <Card title="Capabilities" icon="wand-magic-sparkles" href="/ai/capabilities">
    Explore available MCP tools and features
  </Card>
</CardGroup>