Web Scraping Servers

Provides a bridge for exploring websites with llms.txt files, enabling fetching and parsing of website-specific language model instructions for context-aware interactions in web-based environments.

Scraper.is

Official

Integrates with Scraper.is API to enable web content extraction, structured data parsing, and Markdown conversion for tasks like product research, news aggregation, and content analysis.

AgentQL

Official

Extracts structured data from web pages based on natural language descriptions, converting website content into JSON format without custom scraping code.

pure.md

Official

Enables AI access to web content in clean markdown format through unblock-url extraction and search-web capabilities, bypassing anti-bot measures for reliable information retrieval.

Extracts and processes web content for efficient parsing and analysis of online information

Provides web scraping capabilities with three specialized tools (scrapeFocused, scrapeBalanced, scrapeDeep) for efficient content extraction, image processing, and pagination handling with customizable parameters.

Fetches and converts web pages to markdown format with automatic image extraction and proxy support for accessing content through corporate networks or restricted environments.

Provides a bridge to IETF RFC documents for retrieving, searching, and extracting specific sections from technical standards documentation with support for both HTML and TXT formats

Integrates web browsing capabilities for realtime data retrieval, content extraction, and task automation using popular Python libraries.

Provides tools for accessing Old School RuneScape game data through wiki searches and structured file queries with pagination support

Fetches web content and YouTube video transcripts, converting HTML to Markdown and extracting timestamps for reference in conversations.

AnyCrawl

Official

Integrates with the AnyCrawl API to provide web scraping and crawling capabilities with configurable depth limits, multiple scraping engines, and structured data extraction in various formats including markdown and JSON.

LSD Web Data Extraction

Official

Provides web data extraction and manipulation capabilities through the LSD programming language, enabling structured data retrieval from websites, web searches, and community-created extraction patterns without complex scraping code.

Enables LLMs to make advanced HTTP requests with realistic browser emulation, bypassing anti-bot measures while supporting all HTTP methods, authentication, and automatic response handling for web scraping and API interactions.

Dumpling AI

Official

Provides a bridge to Dumpling AI's data extraction API for performing web searches, scraping content, extracting structured data, and processing various document formats through 20+ specialized tools.

Unifies search and content processing by dynamically selecting optimal providers like Tavily, Brave, and Perplexity to enable flexible information retrieval and enhancement across multiple domains.

Integrates with official French tax websites (impots.gouv.fr, service-public.fr, legifrance.gouv.fr) to provide tax calculations, form guidance, scheme details, and legal article retrieval with automated report generation for French tax professionals and developers.

Bridges AI systems with LinkedIn's API for searching users, retrieving profiles, accessing posts, managing connections, and sending messages to support sales prospecting, recruitment, and professional networking workflows.

Automates reverse engineering of chat interfaces through browser automation and network traffic analysis, capturing streaming API endpoints and providing browser control for analyzing chat APIs without official documentation.

Scrapezy

Official

Integrates with the Scrapezy API to extract structured data from websites based on user-specified prompts, enabling flexible web scraping for data collection, content aggregation, and automated research tasks.

Web Reader

Official Remote

The Web Reader MCP Server is a Z.AI implementation based on the Model Context Protocol (MCP). It provides Claude Code, Cline, and other MCP-compatible clients with powerful web content extraction capabilities, including full-page content retrieval and structured data extraction.