Scrapling MCP Server
local MCP serverScrapling MCP Server is a local MCP server: Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. Install it from pypi as scrapling.
Installation
Terminal
claude mcp add scrapling -- uvx scrapling
Run in your project folder. Add --scope user to use it everywhere.
Claude Desktop, Cursor & other clients
Add to claude_desktop_config.json or .cursor/mcp.json.
{
"mcpServers": {
"scrapling": {
"command": "uvx",
"args": [
"scrapling"
]
}
}
}What you need
- Runtime: Python with uv (runs with uvx) or Docker.
- MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
Summary
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
Scrapling MCP Server vs similar servers
| Server | Stars | Type | API key | Runtime |
|---|---|---|---|---|
| Scrapling MCP Server | 84K | Local | No | pypi |
| fortress | 665 | Local | Yes | pypi |
| SeleniumBase MCP | 13K | Local | No | pypi |
| Firecrawl MCP Server | 7,526 | Local | Yes | npm |
| mcp | 4,325 | Hosted | No | None |
Questions
No. The registry entry lists no keys or environment variables.
Python with uv (runs with uvx) or Docker, plus an MCP client such as Claude Code, Codex, Claude Desktop or Cursor.
Scrapling MCP Server is a local MCP server distributed as the pypi package scrapling.
Run: claude mcp add scrapling -- uvx scrapling
Run: codex mcp add scrapling -- uvx scrapling
Similar MCP servers
NameStars
- fortressio.github.tiliondev/fortress665
- SeleniumBase MCPio.github.seleniumbase/seleniumbase13K
- Firecrawl MCP Serverio.github.firecrawl/firecrawl-mcp-server7,526
- mcpcom.cloudflare.mcp/mcp4,325
- seo-monsterio.github.avansaber/seo-monster391
- MCP for Adobe Premiere Proio.github.leancoderkavy/premiere-pro294
- PyScrappyio.github.mldsveda/pyscrappy260
- scrapeless-mcp-serverio.github.scrapeless-ai/scrapeless-mcp-server169