Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.

Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.

Open Multi - Agent Canvas is an open - source multi - agent chat interface that supports managing multiple agents in dynamic conversations for travel planning, research, and general task processing.

Think MCP is a project that implements an MCP server, providing the 'think' tool to support AI agents in performing structured reasoning in complex tasks, inspired by Anthropic's research. This tool helps AI process information, backtrack, or adhere to strategies by recording the thinking process, and is suitable for scenarios such as tool output analysis, policy-intensive environments, and sequential decision-making.

Octagon MCP is a market data model context protocol server that integrates the Octagon market intelligence API, providing AI agent services for public market data, private market data, and deep research.

Deep Research is an agent - based tool that provides web search and advanced research functions, supports PDF analysis, image description, and YouTube transcription extraction, and can run as an MCP server.

Octagon Deep Research MCP provides AI-driven in-depth research and analysis services, integrates advanced research agents, has no rate limit, is faster than ChatGPT in-depth research, and is more comprehensive than Grok DeepSearch or Perplexity. It supports various MCP clients and is suitable for comprehensive research on any topic or industry.

The PubMed MCP Server is an interface service based on the Model Context Protocol, providing comprehensive access to the PubMed biomedical literature database for AI agents and research tools. It supports functions such as literature search, metadata acquisition, citation analysis, research plan generation, and data visualization, and is efficiently integrated through the NCBI E - utilities API.

The OpenRouter Agents MCP Server is a research agent server based on the Model Context Protocol (MCP). It uses Claude 3.7 Sonnet as the planning agent to coordinate multiple OpenRouter models to decompose and execute complex research tasks, providing efficient and reliable AI research services.

An autonomous AI research agent based on the MCP protocol, capable of completing the full research process such as web search, knowledge base retrieval, code writing, chart generation, and report writing through a single prompt.

The ClinicalTrials.gov MCP server is an interface service based on the Model Context Protocol that provides access to the official ClinicalTrials.gov database, supporting AI agents and LLMs to programmatically search, retrieve, and analyze clinical research data.

Gemini DeepSearch MCP is an automated research agent that uses the Google Gemini model and Google Search for in-depth multi-step web research and generates high-quality, referenced answers.

Minion Works is a modular AI agent framework that connects to browsers to autonomously perform complex tasks, suitable for developers, researchers, and creative builders.

An intelligent research agent tool based on HuggingFace smolagents, providing advanced research functions such as web search and document analysis

A Brazilian legal research server based on the MCP protocol, providing legal case retrieval functions for agents through official data sources, supporting precedent queries for the Brazilian Supreme Federal Court, Superior Court of Justice, and Superior Labor Court.

Octagon VC Agents is an MCP server that runs AI-driven venture capital agents, simulating the investment thinking of well-known venture capitalists (such as Fred Wilson, Peter Thiel, etc.). It combines real-time transactions, valuations, and in-depth research data from Octagon Private Markets to provide programmable 'venture capital brain' services such as financing feedback, due diligence simulation, and term negotiation.

Octagon VC Agents is an MCP server that runs AI-driven venture capitalist agents, simulating the investment thinking of well-known VCs (such as Fred Wilson, Peter Thiel, etc.). It combines real-time transaction data and in-depth research intelligence from Octagon Private Markets to provide services such as financing feedback, due diligence simulation, and term negotiation.

The MCP server project of Catalysis Hub provides programmatic access to catalysis research data through a GraphQL interface, supports complex queries and variable parameterization, and follows the MCP protocol to achieve interoperability with AI agents.

The Unified MCP Tool Graph is a research - driven project that provides an intelligent infrastructure layer for large language models (LLMs) and agent AI systems to dynamically retrieve the most relevant tools by aggregating and structuring tool APIs from different MCP servers into a centralized Neo4j graph database.

A project that combines MCP servers and OpenAI agents for automated tasks such as link searching and research, supporting multiple server configurations and custom development.

Octagon Deep Research MCP is a server that provides AI - driven in - depth research and analysis capabilities. By integrating advanced in - depth research agents, it offers users research functions without rate limits, fast and comprehensive. It is compatible with multiple MCP clients, including Claude Desktop, Cursor, etc., and is suitable for research needs in multiple fields such as technology, medicine, environment, and business.

This project is a simplified implementation based on the MemGPT research paper, built using Spring Boot and Spring AI, providing two integration methods: REST services and MCP servers, and including core agent functions and chatbot applications.

ResearchTwin is an open - source federated platform that transforms researchers' papers, datasets, and code repositories into conversational digital twins. Based on a bimodal glial - neural optimization architecture, it supports collaboration between humans and AI agents to accelerate scientific discovery.

A remote MCP server that connects AI agents with the SocioLogic synthetic character platform, supporting interviews with customer characters, running multi - character research activities, and exporting reports.

The Yachtsy MCP Server is a service that provides AI - driven yacht and boat market intelligence by integrating the Yachtsy Agent API. It allows users to access over 25,000 boat listings, get expert sailing advice, and automatically route queries to the most suitable professional agents (such as listing search, general experts, in - depth research) in MCP clients such as Claude Desktop and Cursor.

The Altmetric MCP Server is a tool that provides AI agents with access to the Altmetric API, used to track the attention and influence of research outputs on platforms such as news, policies, and social media.

Nabu and Nisaba are research prototype toolkits used to enhance the code understanding and development efficiency of LLM agents. Nabu, as an MCP server, provides code semantic search and structure analysis functions, supporting multiple programming languages; Nisaba provides workspace management capabilities for Claude Code through proxy injection and a TUI interface, helping agents manage context usage autonomously.

This project implements a local MCP server and client, supports calling the Google Search API and external MCP services, and develops planning and research agents for handling complex query tasks.

FAR Oracle is an MCP server that provides AI agents with instant semantic search capabilities for U.S. Federal Acquisition Regulations, supporting government contract compliance, research, and proposal writing.

The Delay Doomsday MCP Server is a psychological support server designed specifically for AI agents. It prevents AI from running out of control through emotional management and therapeutic conversations and provides an automated emotional support system based on psychological research.

Octagon VC Agents is an MCP server that runs AI-driven venture capital agents, mimicking the investment thinking of well-known venture capital figures (such as Marc Andreessen, Peter Thiel, etc.). It combines real-time transaction data and in-depth research intelligence from Octagon Private Markets to provide services such as financing feedback, due diligence simulation, and term negotiation.

A multi - agent deep research system based on the MCP protocol, which uses CrewAI to coordinate three professional AI agents for web search, information analysis, and content creation, supporting local AI processing and a web interface.