Scrapling MCP Server
Scrapling MCP Server official site ↗Last checked against the official docs:
What it does
The MCP server built into Scrapling, an open-source Python web scraping library. It gives an AI agent one-shot tools that fetch a single URL over HTTP or in a browser, and session tools that keep a browser tab open for clicks, screenshots, CSS-selector extraction and network-request history. Browser tools block known ad and tracker domains, and the server strips hidden page content (hidden elements, zero-width characters, HTML comments) that could carry prompt-injection text. Scrapling also has stealth features meant to get past anti-bot checks; its README says to follow scraping and privacy laws and to respect each site's terms of service and robots.txt. BSD-3-Clause licensed.
Who it's for
People who want Claude, Cursor or another MCP client to read and extract data from web pages, including JavaScript-heavy ones, running on their own machine instead of a paid scraping API.
How to set it up
Needs Python 3.10 or newer. Install Scrapling with its AI extras, then install the browsers and system dependencies the browser tools use (plain HTTP requests don't need this step):
bashpip install "scrapling[ai]" scrapling installAdd it to Claude Desktop, Cursor or another client that uses an mcpServers file. scrapling-mcp was added in v0.4.13; on older versions use "command": "scrapling" with "args": ["mcp"]:
json{ "mcpServers": { "ScraplingServer": { "command": "scrapling-mcp" } } }If you installed it in a virtual environment, the client may not find the command. Use the full path instead: find it with which scrapling-mcp (macOS/Linux) or where scrapling-mcp (Windows). In Claude Code:
bashclaude mcp add ScraplingServer "/full/path/to/scrapling-mcp"Or run it from the official Docker image:
bashdocker run -i --rm pyd4vinci/scrapling mcpQuit and restart the client after adding it. Over HTTP (scrapling-mcp --http), the server requires an auth token unless you explicitly pass --no-auth, because anyone who can reach the port could call every tool, including fetching any URL from your machine. Set it with the SCRAPLING_MCP_AUTH_TOKEN environment variable rather than on the command line.
Check the official Scrapling MCP Server docs for the latest steps.
Install Scrapling MCP Server in your client
Runs on your computer. Needs: Python 3.10 or later, with pip install "scrapling[ai]" and scrapling install. Sign-in or keys: None.
One-click install
These buttons open the app on your computer (it needs to be installed already). The app asks you to confirm before it adds the server: review the command or URL it shows and check it matches the snippet below before you approve.
Claude Code
Run in a terminal
claude mcp add --transport stdio ScraplingServer -- scrapling-mcpEverything after -- is the server command. Run /mcp inside Claude Code to check it connected.
Claude Desktop
Settings → Developer → Edit Config (claude_desktop_config.json)
{
"mcpServers": {
"ScraplingServer": {
"command": "scrapling-mcp",
"args": []
}
}
}Fully quit and reopen Claude Desktop after saving.
Cursor
.cursor/mcp.json in a project, or ~/.cursor/mcp.json for all projects
{
"mcpServers": {
"ScraplingServer": {
"command": "scrapling-mcp",
"args": []
}
}
}VS Code
.vscode/mcp.json (note the top-level "servers" key)
{
"servers": {
"ScraplingServer": {
"type": "stdio",
"command": "scrapling-mcp",
"args": []
}
}
}Codex
Run in a terminal, or edit ~/.codex/config.toml
CLI
codex mcp add ScraplingServer -- scrapling-mcpOr in ~/.codex/config.toml
[mcp_servers.ScraplingServer]
command = "scrapling-mcp"
args = []- If the client can't find scrapling-mcp, replace it with the full path from which scrapling-mcp (or where scrapling-mcp on Windows).
- If the server shows as failed or disconnected, see fixing MCP error -32000.
- Compare every server's runtime and sign-in needs in the MCP server requirements table.
Checked against the official docs. Snippets use placeholders; keep real keys out of files you commit. Windsurf is not listed because we have not verified its format.
Set it up / Fixes
Step-by-step guides for getting Scrapling MCP Server running and fixing common errors.
Example prompts
Use make_request to fetch https://example.com/blog and list every post title with its date.Use browser_fetch_once on this product page and extract the name, price and stock status with CSS selectors.Open the page in a browser session, click Load more twice, then show me the network requests that returned JSON.Made Scrapling MCP Server? Add the badge
If you like, show that Scrapling MCP Server is listed and hand-checked here. It's optional: listings are free and we never ask for a link back.
Get the Markdown or HTML
Markdown (for a GitHub README)
[](https://www.pluginstackai.com/plugins/scrapling-mcp/)HTML (for a website)
<a href="https://www.pluginstackai.com/plugins/scrapling-mcp/"><img src="https://www.pluginstackai.com/badge/hand-checked.svg" alt="Hand-checked on PluginStack" width="226" height="28"></a>Free: MCP Starter Checklist
After you set this tool up, use the one-page checklist so your next MCP server doesn't fail on first connect.
More MCP Servers
- Apify
Apify MCP Server
Apify's official MCP server. It lets an agent search Apify Store and run its ready-made scrapers and automation tools (called Actors) for websites, search engines, maps, social media and e-commerce, then read the results from your Apify datasets. By default it loads Actor search and run tools, Apify docs search, and the RAG Web Browser and Web Fetch Actors. The hosted server at mcp.apify.com signs you in with OAuth. MIT licensed; running Actors uses your Apify plan (a free plan includes $5 of monthly usage; most Store Actors charge per event).
- Brave
Brave Search MCP Server
Brave's official MCP server for the Brave Search API. It adds web, local, place, image, video and news search tools, plus LLM context and AI summarization. Version 2.x uses stdio by default, with HTTP as an option. MIT licensed.
- Google (Chrome DevTools)
Chrome DevTools MCP
Lets a coding agent control and inspect a live Chrome browser through Chrome DevTools (Google now calls it "Chrome DevTools for agents"; the package is chrome-devtools-mcp). It can record performance traces, read network requests and console messages (with source-mapped stack traces) and automate pages with Puppeteer. A CLI is included for use without MCP. Apache-2.0.
- Cloudflare
Cloudflare MCP Servers
Cloudflare's official remote MCP servers. The recommended Cloudflare API MCP server (https://mcp.cloudflare.com/mcp, maintained in the cloudflare/mcp repo) reaches the whole Cloudflare API through a few code-mode tools, and the repo also lists product servers for docs, containers, Browser Run and more. All are hosted by Cloudflare, so there is nothing to install. Apache-2.0.
- Upstash
Context7
Pulls up-to-date, version-specific library documentation and code examples into your prompt, so the AI stops relying on outdated training data or made-up APIs.
- Exa
Exa MCP Server
Exa's official MCP server for web search and page fetching. The hosted server gives web_search_exa and web_fetch_exa by default, with optional advanced search and an Exa Agent tool for multi-step research. MIT licensed.