"Agentic RAG: Understanding or Exploring Its Meaning and Applications" matching MCP servers:

Enables cited, revision-aware retrieval over real IETF RFC chunks with zero LLM in the answer path, including graph-based supersession resolution and relationship queries via MCP tools.

An MCP-based multi-agent retrieval-augmented generation system that enables question answering over academic papers with hybrid search, knowledge graph multi-hop reasoning, and source-cited answers.

Provides RAG tools with local vector retrieval and web fallback using Firecrawl, enabling document ingestion and querying through MCP stdio transport.

A multi-agent Retrieval-Augmented Generation system exposed as an MCP server. Ask a question and a LangGraph pipeline plans the retrieval, pulls evidence from a pgvector knowledge base, optionally augments it with live web research, drafts a cited answer, and then self-critiques it for grounding — revising until the answer is supported by the sources.

A minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.

An agentic Retrieval-Augmented Generation (RAG) system that combines a small curated machine learning knowledge base with real-time web search capabilities, powered by the Model Context Protocol (MCP).

MCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.

Enables AI assistants to retrieve grounded, cited answers by first searching a local knowledge base and falling back to live web search when needed.

Enables AI agents to search and read 1C:ITS portal subscription materials, such as development standards, platform documentation, and configuration guides, returning content as Markdown with source links.

Enables querying Confluence documents through agentic reasoning over hierarchical document trees, replacing vector similarity with structural navigation.

Enables agents to retrieve relevant context from local documents via MCP tools, supporting ingestion, semantic search, metadata filtering, and evidence inspection entirely on-device.

An intelligent Retrieval-Augmented Generation (RAG) application that uses the Model Context Protocol (MCP) to automatically decide between searching a private knowledge base or the web.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Enables hybrid search and agentic retrieval over Confluence pages via MCP tools, allowing Claude Desktop, Cursor, or Claude Code to search and retrieve Confluence content.

Enables AI agents to perform deep web research by searching, fetching, chunking, retrieving, and synthesizing cited answers from exact source passages via a deep_research tool.

A custom MCP server that turns Claude into an agentic shopping assistant for searching products, comparing options, managing a cart, and checking out with built-in guardrails for safe autonomous commerce.

Hybrid RAG over Claude Code and Hermes session history via MCP tools for search, ingest, and context injection.

A CLI tool and MCP server that turns markdown documentation into a searchable, queryable knowledge base.

MCP server for Fathom Works RAG that exposes a self-hosted knowledge base as tools for any MCP-capable LLM to query documents, manage libraries, and ingest files or URLs.

Enables AI agents to query Austria's entire company register (Firmenbuch) in plain language, providing official master data, annual accounts, and key ratios from a multi-tenant MCP server.