Web Scraping & Data Collection MCP Servers

French Open Data & IGN

Provides Claude access to a comprehensive suite of French public open data, national mapping services, address geocoding, and administrative geographical information.

Wanyi Watermark

Extracts watermark-free videos and images from Douyin and Xiaohongshu, offering video link parsing and text transcription.

Goodreads GetGather

Accesses and retrieves book data from Goodreads user libraries.

ABS

Provides AI assistants access to query and analyze statistical data from the Australian Bureau of Statistics (ABS) via the SDMX-ML API.

Standards Finder

Programmatically access and parse IETF RFCs, Internet Drafts, and OpenID Foundation specifications.

Google Images Search

Integrates Google Images search directly into your chat interface, displaying visual results and enabling direct saving to your project.

RedNote Downloader

Enables agents to download Xiaohongshu content, including images, videos, and LivePhotos, and retrieve detailed work information via URL.

Opendata

Simplifies access and exploration of Korean Public Data Portal (OpenAPI) resources.

Codeforces

Accesses the Codeforces API to provide comprehensive contest, user, and submission data through a standardized MCP interface.

ArxivSearcher

Intelligently searches Software Engineering papers on arXiv, offering advanced filtering, sorting, and management capabilities.

Pitchlense

Analyze startup investment risks using AI-powered assessment across multiple categories, leveraging the Model Context Protocol.

Webustler

Extracts clean, LLM-ready markdown content from any URL, automatically bypassing anti-bot protections like Cloudflare.

MedRxiv

Enables AI assistants to search and access health science preprints from medRxiv.

Biomart

Interfaces with Biomart databases using the Model Context Protocol (MCP) to provide biological data to Large Language Models.

Pearch.ai

Integrates advanced people search functionality into applications via a FastMCP service.

Bibliothèque Nationale de France

Accesses the Gallica API from the Bibliothèque nationale de France (BnF) to generate sequential research reports.

LLM Jukebox

Enables large language models to seamlessly search, download, and extract information from YouTube music videos.

EVE Online Market

Provides a Model Context Protocol server for accessing EVE Online market data via the ESI API.

LinkedIn Posts Hunter

Automate LinkedIn job post search and management via AI assistants by scraping and organizing relevant opportunities with local data storage.

Terrorblade

Unifies data extraction and parsing from messaging platforms, standardizing information for analytics and AI applications.