Web Scraping & Data Collection MCPサーバー

Perplexica

22,134

Provides an open-source AI-powered search engine alternative to Perplexity AI.

GPT Researcher

21,635

Conducts in-depth web and local research on any topic, generating comprehensive reports with citations.

Skyvern

13,472

Automates browser-based workflows using LLMs and computer vision for robust and adaptable web interactions.

PyMuPDF

7,177

Enables data extraction, analysis, conversion, and manipulation of PDF, XPS, and eBook documents in Python.

Steel Browser

4,345

Automates web interactions for AI agents and applications without managing infrastructure.

Trafilatura

4,322

Extracts text and metadata from web pages and online resources, offering various output formats.

YouTube Transcript

3,972

Retrieves transcripts and subtitles from YouTube videos, including automatically generated ones, without requiring an API key or headless browser.

ENScan Go

3,649

Collects and aggregates domestic enterprise information from various sources to aid in reconnaissance tasks.

Firecrawl

3,264

Empowers LLMs with advanced web scraping capabilities for content extraction, crawling, and search functionalities.

Browserbase

1,790

Enables LLMs to control cloud browsers for web interaction, data extraction, and task automation using Browserbase and Stagehand.

Browser

1,772

Enables AI applications to control a user's existing browser instance.

Agent Twitter Client

1,678

Automates interactions with Twitter, including scraping data, sending tweets, and engaging with Grok AI, all without needing the official Twitter API.

DevDocs

1,584

Crawls, extracts, and organizes technical documentation into an LLM-ready format, streamlining research and implementation for developers.

Zenfeed

949

Empowers RSS with AI to automatically filter, summarize, and deliver important information, reducing information overload.

Mobile Next

802

Enables scalable mobile automation through a platform-agnostic interface for interacting with native iOS/Android applications and devices.

Notte

741

Enables the development, deployment, and scaling of web browsing agents through a single API.

Fetcher

705

Fetches web page content using a Playwright headless browser, enabling JavaScript execution and intelligent content extraction.

RedNote

529

Access content from the RedNote (XiaoHongShu) platform via an MCP server.

Crawl4AI RAG

451

Empowers AI agents and coding assistants with web crawling and retrieval-augmented generation (RAG) capabilities.

Deepwiki

430

Fetches and converts Deepwiki content to Markdown for use in code editors and other MCP-compatible clients.