Web Scraping & Data Collection MCP Servers

Jina AI Grounding

Enhances LLM responses with factual, real-time web content via Jina.ai's Grounding API.

Deep Web Research

Enhances web research capabilities for large language models through intelligent search queuing and content extraction.

Scrappey

Control a browser through an LLM using Scrappey's web automation and scraping capabilities.

Crypto

Provides Claude AI with real-time cryptocurrency data from the CoinMarketCap API.

iReader

Extracts content from various online sources, including webpages, YouTube videos, tweets, and PDFs.

LinkedIn Profile

Serves LinkedIn profile data via the Model Context Protocol (MCP) for integration with AI models like Anthropic.

Jina AI

Converts web pages into Markdown format, optimized for large language models.

Exa

Enables AI assistants to access real-time web information and specialized search capabilities via the Exa AI Search API.

Exa

Connects AI assistants with the Exa AI Search API to provide real-time web information and specialized search tools.

DadosBR

Integrates Brazilian company (CNPJ) and postal code (CEP) data lookup into various AI assistants via Model Context Protocol.

WeChat Article Tools

Automates the retrieval, searching, and summarization of WeChat public account articles.

Government of Canada Data

Accesses Canada's Open Government data for comprehensive dataset discovery and provides specialized querying for national transportation infrastructure information.

Bybit Announcements

Enables AI agents to efficiently fetch, track, and act on Bybit cryptocurrency exchange announcements.

Peeky Search

Extracts relevant web page excerpts based on IR methods, providing direct evidence instead of AI-generated summaries.

Web Research

Empower AI agents with comprehensive web research capabilities, including searching, fetching, and synthesizing information.

GitHub Portfolio

Expose tools for AI agents to query a GitHub user's public profile, repositories, languages, and README content.

LinkedIn Buddy

Automates LinkedIn interactions, offering a CLI, an MCP server, and a TypeScript toolkit for managing inbox, search, feed, jobs, and profiles with safe, confirmed actions.

RSSdeck

Transforms RSS feeds into token-efficient, AI-ready data for agents through an MCP server.

Thalora

Provides a pure Rust, full-featured web browser designed for AI agents, offering Chrome 131 compatibility and AI memory persistence without external dependencies.

Purroxy

Records user interactions on any website to securely automate tasks and provide AI access to authenticated sessions.