发现我们为 web scraping & data collection 精心策划的 MCP 服务器集合。浏览 1653 个服务器,找到满足您需求的完美 MCP。
Enables unstructured document processing for AI chatbots by extracting data from PDF files.
Downloads YouTube subtitles using yt-dlp and connects them to claude.ai via Model Context Protocol.
Scrapes content from webpages, extracting text, HTML, or markdown.
Connects AI assistants to ReviewWebsite.com API for managing website reviews and extracting data.
Converts HTML content from URLs or raw input into clean, formatted Markdown using Turndown.js.
Collects patent-related information from PatSnap's API for trend analysis and reporting.
Integrates with Goodreads to retrieve a user's book library.
Enables Claude to perform web searches using the Perplexity AI API and provide answers with citations.
Queries Uniswap pools and pairs by token address, delivering structured data for analysis and integration.
Analyzes blockchain wallet data and token information via the Dune API for AI assistants and MCP clients.
Integrates privacy-focused Presearch capabilities and web content scraping with AI assistants using the Model Context Protocol.
Provides access to health-related data in Hong Kong through a FastMCP interface.
Facilitates personalized video content selection for AI by providing access to Bilibili user data and search functionalities.
Find the lowest prices for grocery products across various chain markets in Turkey.
Integrates Exa's Websets API with MCP-compatible clients like Claude Desktop, Cursor, and Windsurf to manage dynamic collections of web entities.
Searches and fetches scientific papers from arXiv.org based on category and number of results.
Provides AI assistants access to query and analyze Australian Bureau of Statistics data through the SDMX-ML API.
Executes Google searches and extracts results by bypassing anti-bot mechanisms, offering both command-line and real-time search capabilities for AI assistants.
Access live NHL game data, scores, stats, teams, and generate reports using the Model Context Protocol.
Retrieves and processes web content in various formats for use with Large Language Models.
Scroll for more results...