# Scrapling (slim)

> Scrapling is an open-source Python web scraping library by Karim Shoair, with fast HTTP requests, stealth browsers, adaptive parsing, spiders and a local MCP server of 17 tools for AI agents.

- Full: https://www.anchorterminal.com/tools/scrapling.md (~7,150 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/scrapling.json · canonical https://www.anchorterminal.com/tools/scrapling
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18 · pricing https://www.anchorterminal.com/tools/scrapling#pricing · reviews https://www.anchorterminal.com/tools/scrapling#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 68.5/100 · rank #380 of 1557 · #10 in Web scraping & crawling · not agent-ready · confidence high**


Assessment: Scrapling's MCP server gives agents 17 typed tools with read-only and destructive hints, output trimming by CSS selector and default stripping of hidden page text. It is pre-1.0 (0.5.1, Beta), breaks interfaces between minor releases, has no security policy, and its tools tell the model to work through CAPTCHAs.

## Facts

- Kind: MCP server · vendor: Karim Shoair · category: Web scraping & crawling · legal entity: not named · provenance 39/100
- Local only (stdio, Streamable HTTP): pypi `scrapling`
- Auth: None · pricing: Free · x402: no · licence: BSD-3-Clause
- Benchmark probes: not run yet, so Performance is pending
- Surface listed: The local MCP server in the `scrapling` package (`scrapling-mcp` or `scrapling mcp`), over stdio or a self-run streamable HTTP port. Read from a clone of github.com/D4Vinci/Scrapling at commit 2998c9e (17 November 2026), and on 18 November from the docs site, the repository page, its issues and the MCP registry. No tool was run
- MCP tools: make_request, browser_fetch_once, browser_open, open_request_session, browser_fetch, session_make_request, browser_extract, browser_actions, browser_evaluate, browser_screenshot, browser_observe, browser_network_requests, browser_network_request, browser_save_state, browser_load_state, list_sessions, close_session
- Library: Fetchers for plain HTTP with browser impersonation (curl_cffi), Playwright and a stealth Patchright browser, an adaptive parser, Scrapy-like spiders that read robots.txt, and a CLI and interactive shell
- HTTP transport: `scrapling-mcp --http` binds 127.0.0.1 by default and needs `--auth-token` or `SCRAPLING_MCP_AUTH_TOKEN`, or an explicit `--no-auth`. `--allowed-host` turns on DNS-rebinding protection
- Limits: Network history keeps 1,000 requests and 20 MiB of bodies per session and skips bodies over 1 MiB, per the server instructions
- Sponsors: The README and every page of the docs site carry paid placements for proxy, CAPTCHA-solving and bot-protection bypass services

- Scores: Reliability 65, Performance not tested, Schema & documentation 81, Agent ergonomics 71, Security & auth 39, Payments & pricing 90, Task success not tested, Maintenance & community 93, Transparency & trust 52
- Why: Reliability, Read on the local-software lines, since the MCP server runs on the user's machine over stdio or a self-run HTTP port. · Schema & documentation, Read from the server source (scrapling/core/ai/server.py) and docs/ai/mcp-server.md in the repository. · Agent ergonomics, 17 tools, and v0.5 and v0.5.1 both shortened the descriptions. · Security & auth, Read as local software with an optional HTTP transport. · Payments & pricing, Free, self-hosted software under BSD-3-Clause with nothing to buy, read with the self-hosted rule. · Maintenance & community, v0.5.1 tagged and released on 4 November 2026, 14 days before 18 November (30). · Transparency & trust, BSD-3-Clause in LICENSE and the PyPI classifiers (30).
- Sources: 14, open questions: 4, both in the full twin
- Capabilities: web.scrape, web.extract, web.crawl, scraping.js-render, scraping.anti-bot, scraping.proxies, browser.control
- JSON: https://www.anchorterminal.com/api/v1/tools/scrapling.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: Discord https://discord.gg/EMgGbDceNQ; https://scrapling.readthedocs.io; https://github.com/D4Vinci/Scrapling/issues; more in the full twin

## Before you call it

1. Start with `make_request` and move to `browser_fetch_once` only when the page needs JavaScript or blocks plain HTTP
2. Pass `css_selector` on fetch tools to cut output. Snapshots need one match or no selector
3. Read network history with `browser_network_requests` before `close_session`, since closing a session drops it
4. Check the target site's terms and robots.txt yourself. The MCP tools don't read robots.txt, only the spiders do
5. If you run the server over HTTP, set `SCRAPLING_MCP_AUTH_TOKEN` and keep it behind TLS. The token travels in clear over plain HTTP

## Connect

```bash
pip install "scrapling[ai]" && scrapling install
```

```bash
claude mcp add ScraplingServer -- scrapling-mcp
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/scrapling

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Outcrawl | B | 64.9 | web.scrape, web.crawl, web.extract, browser.control, scraping.proxies, scraping.js-render, scraping.anti-bot | https://www.anchorterminal.com/tools/outcrawl.min.md |
| Scrapfly | BB | 77 | web.scrape, web.extract, web.crawl, scraping.proxies, scraping.js-render, scraping.anti-bot | https://www.anchorterminal.com/tools/scrapfly.min.md |
| Spider | BB | 74.3 | web.scrape, web.extract, web.crawl, scraping.proxies, scraping.js-render, scraping.anti-bot | https://www.anchorterminal.com/tools/spider-cloud.min.md |
| Browserless | BB | 70.4 | browser.control, scraping.js-render, scraping.anti-bot, scraping.proxies, web.scrape, web.crawl | https://www.anchorterminal.com/tools/browserless.min.md |
| Olostep | B | 68.6 | web.scrape, web.extract, web.crawl, scraping.proxies, scraping.js-render, scraping.anti-bot | https://www.anchorterminal.com/tools/olostep.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)

