Web & Search

Exa (formerly Metaphor) is a neural search engine designed specifically for AI agents and Large Language Models (LLMs) to retrieve high-quality, structured web data. It differentiates itself by using a transformer-based 'link prediction' model that understands semantic meaning rather than just matching keywords, making it a primary choice for RAG and autonomous research applications.

Exa Websets is an AI-native research and data enrichment engine designed to build structured, verified collections of companies, people, and research papers from the live web. Unlike traditional keyword-based scrapers, it uses neural search to understand complex natural language queries and automatically enriches results with custom data points like CEO names or funding stages.

Notion is an all-in-one productivity platform that combines notes, tasks, wikis, and databases into a highly customizable block-based workspace. It is designed for individuals and teams looking to consolidate fragmented tools into a single source of truth. Its key differentiator is its unique database-meets-document architecture, allowing users to build bespoke workflows from scratch.

MTG Chinese Card Database (sbwsz-mcp) is an open-source Model Context Protocol (MCP) server that provides AI agents with direct access to localized Magic: The Gathering card data. It enables complex, natural-language card queries and unique visual generation tools specifically for the Chinese-speaking MTG community.

Next.js Tailwind Assistant is an open-source Model Context Protocol (MCP) server that provides AI agents with real-time access to Next.js 15+ and Tailwind CSS documentation. Designed for developers using AI-first IDEs like Claude or Cursor, it differentiates itself by offering pre-indexed Catalyst UI components and professional design patterns directly to the LLM's context.

Linkup is a production-grade web search API designed specifically for AI agents and LLMs to provide real-time, fact-checked grounding. It differentiates itself through state-of-the-art performance on benchmarks like OpenAI's SimpleQA and a flat, predictable pricing model that undercuts competitors like Perplexity and Exa.

tcmb_mcp is an open-source Model Context Protocol (MCP) server that provides AI assistants with direct access to Turkish Central Bank (TCMB) exchange rate data. It enables developers and financial analysts to fetch historical rates dating back to 1996 and perform currency conversions with built-in holiday awareness.

RSS Reader by kwp-lab is a Model Context Protocol (MCP) server that enables AI agents, specifically Anthropic's Claude, to subscribe to and read RSS feeds. It allows LLMs to fetch live news entries and extract clean article content in Markdown format for real-time analysis. It is primarily for developers building agentic workflows that require automated information monitoring.

WebSim Explorer is an open-source Model Context Protocol (MCP) server designed to search, filter, and analyze the vast ecosystem of AI-generated simulations on WebSim.ai. It is a specialized utility for developers and power users who want to programmatically discover trending projects, track influential creators, and curate digital assets. Its key differentiator is the ability to integrate WebSim’s database directly into AI environments like Claude Desktop for real-time research.

Gmail is the world's most popular email service, providing end-to-end message management, advanced spam filtering, and deep integration with Google Workspace. It serves everyone from casual individual users to global enterprises, setting itself apart with a powerful search-driven interface and a robust API for inbox automation.

Korean Law Search (lexlink-ko-mcp) is a Model Context Protocol (MCP) server that connects AI assistants like Claude and Cursor directly to the official South Korean National Law Information Center. It is designed for legal professionals and developers who need to perform structured, natural-language research on Korean statutes and administrative rules. Its key differentiator is the ability to drill down into specific article hierarchies and access English translations within an AI-native workflow.

Web Scout is a free, privacy-focused MCP server that enables AI assistants to perform web searches and extract clean webpage content without requiring paid API keys. It serves as a lightweight bridge for developers using tools like Claude Desktop or Cursor to provide their AI agents with real-time internet access via DuckDuckGo.

Grokipedia-MCP is a Model Context Protocol (MCP) server that enables AI agents to programmatically search, retrieve, and analyze articles from xAI's Grokipedia encyclopedia. It provides specialized tools for full-text retrieval, citation extraction, and guided research workflows, acting as a bridge between LLMs like Claude and xAI’s AI-curated knowledge base.

Context7 is a specialized retrieval-augmented generation (RAG) tool designed to provide AI coding assistants with up-to-date, version-specific documentation. It eliminates LLM hallucinations by fetching real-time code snippets and API references directly from official sources into prompts via the Model Context Protocol (MCP).

A Model Context Protocol (MCP) server that connects AI agents to Semantic Scholar and arXiv for real-time academic research. It is designed for researchers and developers who need LLMs to perform grounded literature searches, citation analysis, and full-text PDF extraction. Its key differentiator is the ability to fetch full-text content from arXiv and Wiley open-access sources without requiring an upfront API key.

YouTube-MCP is a Model Context Protocol server that allows AI agents like Claude to interact directly with YouTube content, including searching videos and fetching deep metadata. It is primarily for researchers and developers who need to perform automated video analysis, summarization, and RAG (Retrieval-Augmented Generation) without manual copy-pasting. Its key differentiator is the ability to retrieve timestamped, multilingual transcripts natively within an AI's context window.

Google Drive is a ubiquitous cloud storage and collaboration platform that allows users to store, share, and edit files in real-time. It is designed for everyone from individual consumers to large enterprises, with its key differentiator being its seamless, deep integration with the Google Workspace ecosystem and its powerful AI-driven search capabilities.

Paper Search is an open-source Model Context Protocol (MCP) server designed to give AI agents direct access to global academic repositories. It enables researchers to search, retrieve metadata, and extract full-text content from sources like arXiv and PubMed through a unified interface. Its key differentiator is the support for eight simultaneous academic platforms, streamlining the transition from discovery to deep analysis within LLM workflows.

Brave Search is an independent search engine and API providing privacy-focused, structured web data without reliance on Google or Bing indexes. It is designed for developers and AI creators who need high-quality grounding data for RAG (Retrieval-Augmented Generation) applications. Its key differentiator is its completely independent web index and specialized LLM-ready endpoints.

NGSS Standards Explorer is a specialized Model Context Protocol (MCP) server that provides AI agents with structured access to the Next Generation Science Standards. It is designed for educators and developers to help AI models navigate complex three-dimensional science frameworks (SEPs, DCIs, and CCCs) for curriculum planning and standards alignment.