Scrapling MCP
v1.2.0Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) to call the `scrapling` MC...
⭐ 0· 1.6k·15 current·16 all-time
byBurak@devbd1
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Scrapling MCP web scraping) match the files and instructions: guidance, recipes, MCP setup, and two helper Python scripts that call Scrapling fetchers. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md focuses on scraping strategy, MCP configuration, and mcporter usage. Instructions reference only Scrapling APIs, proxy examples, and local crawl dirs. There are no instructions to read unrelated system files or exfiltrate secrets; the guidance repeatedly admonishes permissioned use for anti-bot/stealth modes.
Install Mechanism
No install spec is present (instruction-only), so nothing is automatically downloaded or written during install. The README suggests optional pip installs for Scrapling and Playwright, which is appropriate and expected for the skill's functionality.
Credentials
The skill declares no required environment variables, credentials, or config paths. Examples show optional PYTHONPATH and proxy URL examples (including example user:pass formats), which are reasonable for a scraping tool and proportionate to the stated purpose.
Persistence & Privilege
always:false and model invocation is not disabled (default), which is normal. The skill does not request persistent platform privileges or attempt to modify other skills or global agent config beyond advising the user how to add an MCP server entry for Scrapling.
Assessment
This skill appears coherent for web-scraping with Scrapling, but review and follow these precautions before use: 1) Ensure you have explicit permission to scrape target sites and comply with terms of service and law — the skill includes anti-bot/stealth features that should not be used to evade access controls. 2) Installing Playwright will download browser binaries; verify the install commands and their source. 3) Sample proxy examples include credentials in URLs — treat any real proxy credentials as sensitive and provide them only to trusted providers. 4) The included scripts write files (downloads, crawldir). Run in a controlled directory and inspect the code if you will run them. 5) If you run Scrapling as an MCP server, consider binding it to localhost and review its network surface before exposing it. 6) If you need higher assurance, verify the upstream Scrapling project (repo/docs links are provided) and review the included Python scripts for any local modifications.Like a lobster shell, security has layers — review code before you run it.
latestvk97djhyvjrt5n5gaav4bzgaz7h82cnhm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.