AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Browser Automation/
PyScrappy
PyScrappy logo

PyScrappy

Active·★ 264·MIT·Updated 2026-10-22

PyScrappy is an AI-native web scraping toolkit designed to transform websites into structured, LLM-ready data. It can be used as a standalone Python library or exposed as an MCP server, enabling AI agents to directly access and process web information.

PyScrappy sits in the Browser Automation category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Generic web scraping with structured text, links, images, and tables output.. A representative use case is Empowering AI agents (e.g., Claude, Ollama) to fetch and integrate real-time web data.. The listed license is MIT. GitHub stars are currently 263. Relevant tags include Web Scraping, AI Agents.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#Web Scraping#AI Agents#LLM Data Preparation#Python Library#MCP Server#Data Extraction#Browser Automation#API Integration
$ Install
$ pip install pyscrappy
↗ Visit site★ GitHub
01

Features

01Generic web scraping with structured text, links, images, and tables output.
02LLM-ready output in Markdown, JSON, and DataFrame formats.
03MCP server functionality to expose scrapers as tools for AI agents.
04Optional Playwright backend for JavaScript rendering on dynamic websites.
05Support for proxies and scraping API services to bypass blocking.
02

Why choose it

+Generic web scraping with structured text, links, images, and tables output.
+LLM-ready output in Markdown, JSON, and DataFrame formats.
+Empowering AI agents (e.g., Claude, Ollama) to fetch and integrate real-time web data.
+Supports 6 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Python
Runtime
Verified via docs
Playwright
JS Rendering
Verified via docs
Pandas
DataFrames
Verified via docs
MCP (Model Context Protocol)
Agent Protocol
Verified via docs
AI Agents
Integration
Verified via docs
Scraping API Services
Anti-bot
Verified via docs
05

Quick start

1
$ pip install pyscrappy
06

Use cases

↳Empowering AI agents (e.g., Claude, Ollama) to fetch and integrate real-time web data.
↳Transforming arbitrary web content into clean, structured data for large language models.
↳Collecting specific information from popular sites using dedicated built-in scrapers (e.g., Wikipedia, IMDB, Amazon).
↳Custom data extraction from any URL using CSS selectors.
↳Extending scraping capabilities through custom plugins for new data sources.
07

Alternatives

⚡Top VS:
VSfitter★133→VSstealth-chrome-devtools-mcp★30→VStap★18→VSoya-browser★354→
fitter logo
fitter★ 133
New way for collect information from the API's/Websites
VSCompare→
stealth-chrome-devtools-mcp logo
stealth-chrome-devtools-mcp★ 30
Undetectable browser automation for AI agents via MCP. Stealth Chrome DevTools with smart profile management, anti-detection arg filtering, and CDP access.
VSCompare→
tap logo
tap★ 18
Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.
VSCompare→
oya-browser logo
oya-browser★ 354
The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome, with persistent personas, CAPTCHA and MFA handling, and live human takeover.
VSCompare→
cloakbrowser-mcp logo
cloakbrowser-mcp★ 172
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
VSCompare→
aginxbrowser logo
aginxbrowser★ 54
The browser built for AI agents — fetch live pages as markdown, render JS/SPAs with built-in V8, take screenshots without Chromium, meta-search 5 engines, and drive interactive login sessions. One Rust binary, stealth TLS fingerprints, MCP native for Claude Code & Cursor. Headless browser alternative to Puppeteer/Playwright.
VSCompare→
mcp-browser-use logo
mcp-browser-use★ 62
FastAPI server implementing MCP protocol Browser automation via browser-use library.
VSCompare→
wigolo logo
wigolo★ 5.5k
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
mldsveda /
PyScrappy
↗

Python web scraping toolkit and MCP server that gives AI agents clean, structured web data from any URL or built-in scrapers.

264MIT
Last commit6d ago
StatusActive
CategoryBrowser Automation
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.