Skip to content
MCP server

Scrapling MCP Server

MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

Runs locallyActively maintainedStatus and history

The repository was last updated 3 days ago and is published under BSD-3-Clause.

Pricing
Open source
Platforms
CLI, self-hosted, Linux
Runs
Locally
GitHub stars
104K
Last commit
3 days ago
Language
Python

About Scrapling MCP Server

Scrapling MCP Server is an open-source MCP server for web search and scraping. It runs locally on your machine and is started by your AI client.

Scrapling MCP Server brings the Scrapling scraping library to AI chat clients and agents. It exposes seventeen tools for fetching pages, either as one-shot calls or inside persistent sessions.

One-shot tools fetch a single URL and clean up after themselves. Session tools keep cookies and settings, let the AI continue on the same tab, inspect network history, take screenshots, and run chained browser actions. Login state can be saved to and restored from a file.

It targets developers who want an assistant to collect data from dynamic or protected sites through conversation.

Install

Run in a terminal

claude mcp add scrapling -- uvx scrapling

Add to claude_desktop_config.json

{
  "mcpServers": {
    "scrapling": {
      "command": "uvx",
      "args": [
        "scrapling"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "scrapling": {
      "command": "uvx",
      "args": [
        "scrapling"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "scrapling": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "scrapling"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "scrapling": {
      "command": "uvx",
      "args": [
        "scrapling"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "scrapling": {
      "command": "uvx",
      "args": [
        "scrapling"
      ]
    }
  }
}

Tools this server provides (17)

Taken from the project documentation; the running server may differ.

make_request
One-shot HTTP request with fingerprint impersonation.
browser_fetch_once
Render and scrape one URL with a stealth browser.
browser_open
Open a persistent stealth browser session.
open_request_session
Open a persistent HTTP request session.
close_session
Close a browser or request session.
list_sessions
List active sessions and their settings.
browser_save_state
Save cookies and storage to a file.
browser_load_state
Restore saved state into an open session.
browser_fetch
Fetch a URL through an open browser session.
session_make_request
Send an HTTP request through a request session.
browser_screenshot
Capture the page or an element as an image.
browser_observe
Return a short image sequence of page changes.
browser_extract
Read current page content as snapshot, HTML, Markdown or text.
browser_actions
Chain clicks, typing, waits and dialog replies.
browser_evaluate
Evaluate script in the current page.
browser_network_requests
List network requests made by the page.
browser_network_request
Inspect a single network request.

What it does

HTTP requests
Fast requests with browser fingerprint impersonation.
Stealth browser fetch
Renders JavaScript pages with fingerprint spoofing and Cloudflare challenge handling.
Persistent sessions
Browser and request sessions that keep cookies across calls.
Saved login state
Save and reload cookies, local storage and IndexedDB.
Page extraction
Read pages as snapshot, HTML, Markdown or text.
Chained actions
Combine clicks, typing and waits in one call.

Good for

  • Scrape dynamic JavaScript sites
  • Reuse a logged-in session for extraction
  • Capture screenshots of page elements
  • Inspect network requests of a page
  • Automate form filling during scraping

Pricing

Open source

Prices change. Check scrapling.readthedocs.io before you buy.

Scrapling MCP Server FAQ

How many tools are there?

Seventeen, split into one-shot and session tools.

How is it installed?

Registry packages are a PyPI package and a container image, both over stdio.

What license applies?

BSD-3-Clause.

Where are saved state files stored?

On the machine running the MCP server.

Is Scrapling MCP Server free?

Yes. Scrapling MCP Server is open source, so you can use and self-host it for free.

How do I add Scrapling MCP Server to Claude Code?

Run this command in your terminal: claude mcp add scrapling -- uvx scrapling

What are the best alternatives to Scrapling MCP Server?

The closest alternatives to Scrapling MCP Server are Browser Use, Firecrawl MCP Server, SearXNG Search, Oya Browser and Mantis.

Alternatives to Scrapling MCP Server

  1. Browser Use

    MCP server

    Browser agents and cloud browsers for AI, with an MCP server for web tasks

    • 7 tools
    • Remote
    • Freemium
    • 121K GitHub stars
    • Browser automation
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  4. Oya Browser

    MCP server

    HIPAA-oriented agentic browser with replayable playbooks, reachable over MCP

    • 32 tools
    • Remote
    • Freemium
    • 349 GitHub stars
    • Browser automation
  5. Mantis

    MCP server

    Browser MCP server that gives agents numbered text pages instead of screenshots

    Runs locally
    • 1 tool
    • Open source
    • 5 Hacker News points
    • Browser automation
  6. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping