AI & Machine Learning

Blockscout MCP is a server implementation that connects AI agents to real-time blockchain data across 3,000+ EVM chains through the Model Context Protocol. It is designed for developers and analysts using AI IDEs and assistants like Claude or Cursor to query on-chain balances, tokens, and contract metadata. Its key differentiator is its sophisticated context management, including response slicing and progress notifications to prevent LLM context overflow.

Cookiy is an agentic user-research platform that operates as a Model Context Protocol (MCP) server for AI coding agents like Claude Code and Cursor. It allows developers to delegate end-to-end qualitative research—from study design and participant recruitment to conducting AI-moderated voice interviews and generating reports—directly from their IDE.

LlamaIndex is a comprehensive data framework designed to connect custom data sources to large language models for RAG and agentic workflows. It specialized in the "data engineering" side of AI, offering a high-performance document parsing engine (LlamaParse) that excels at converting complex PDFs, tables, and images into LLM-ready formats. It is the go-to choice for developers who need to build knowledge-intensive applications with high retrieval precision.

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.

NPM Sentinel is an AI-native Model Context Protocol (MCP) server that provides real-time security, dependency, and performance intelligence for NPM packages. It is specifically designed for developers using AI agents like Claude to automate the vetting and auditing of software libraries directly within their coding workflows.

SpotDB is a secure, ephemeral SQL sandbox powered by DuckDB that allows AI agents to query and analyze CSV or Parquet files through the Model Context Protocol (MCP) or a REST API. It is designed for developers who need to give LLMs data analysis capabilities without the risk of exposing production databases or managing complex infrastructure. Its key differentiator is its native MCP integration, enabling instant 'plug-and-play' SQL tools for assistants like Claude.

Lotus Wisdom is an MCP (Model Context Protocol) server that implements a contemplative reasoning framework inspired by the Lotus Sutra. It is designed for researchers and strategists to guide AI through non-linear "wisdom journeys" to solve complex, paradoxical problems where traditional logic fails. Its key differentiator is the integration of meditative pauses and specific meta-cognitive domains into the AI's internal reasoning loop.

Klavis AI (specifically its Strata platform) is a specialized infrastructure layer that allows AI agents to interact with thousands of tools using the Model Context Protocol (MCP). It is designed for developers who need their agents to navigate complex SaaS ecosystems reliably without overwhelming the LLM's context window. Its key differentiator is 'progressive tool discovery,' which guides agents through APIs step-by-step rather than dumping all documentation into the prompt at once.

Context Awesome is a specialized knowledge retrieval tool that connects AI agents to a massive database of over 8,500 community-curated "awesome" lists from GitHub. It is designed for developers and researchers who need their AI systems to find vetted tools and libraries while minimizing the risk of hallucinations or outdated information. Its key differentiator is the high signal-to-noise ratio of its data, which relies on expert-curated repositories rather than unfiltered web scrapes.

StacksFinder is a Model Context Protocol (MCP) server that provides AI agents with deterministic, data-driven technology stack recommendations and comparisons. It is designed for developers and architects to eliminate LLM hallucinations by providing structured analysis across six dimensions directly within AI-powered IDEs like Cursor and Claude.

Google Scholar Search (MCP) is an open-source Model Context Protocol server that bridges AI models like Claude, Gemini, and Cursor with academic data. It allows AI agents to perform real-time scholarly searches and retrieve paper metadata through a standardized, streamable interface. It is primarily designed for researchers and developers building autonomous AI research assistants.

MCP Analytics is a specialized Model Context Protocol (MCP) server that connects real-time e-commerce and financial data from platforms like Shopify and Stripe directly to Claude and Cursor. It is designed for data-driven merchants and developers who want to perform complex forecasting and statistical analysis using natural language without manual CSV exports.

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).

Explorium MCP (AgentSource) is a Model Context Protocol server that connects AI agents to live B2B company and contact data. It's designed for developers and sales teams to automate lead enrichment and business research directly within LLM environments like Claude Desktop or Cursor. Its key differentiator is the 'AgentSource' infrastructure, which provides structured, verified business intelligence specifically optimized for agentic tool-calling.

Macrostrat-MCP is a specialized Model Context Protocol server that connects AI models to the vast Macrostrat geological database, enabling natural language queries about bedrock and stratigraphy. It is designed for geoscientists and developers who need to integrate high-fidelity geological context into AI-driven research workflows. Its primary differentiator is the ability to bridge complex, coordinate-based earth science data with conversational AI agents.

A specialized Model Context Protocol (MCP) server that bridges the Contabo Cloud API with AI agents like Claude. It allows developers to manage VPS infrastructure and object storage through natural language commands without writing custom integration code.