"How to allow an LLM to ask questions to a user" matching MCP servers:

MCP server that ingests PDF documents into pgvector for semantic search and RAG pipelines. It handles extraction, chunking, local embeddings, and storage, enabling agents to make PDFs searchable via natural language.

A lightweight RAG system that provides an MCP server for searching and interacting with vector-based knowledge bases. It enables users to perform retrieval-augmented generation and search across Qdrant collections through a standardized interface.

Enables MCP-capable agents to retrieve relevant slices of a user-story knowledge graph (stored in Supabase + pgvector) using three retrieval verbs: find_related, find_crossover, and query_stories.

Enables users to ingest PDF/DOCX/TXT/MD documents and ask natural language questions about them, using local embeddings and Groq-powered retrieval-augmented generation.

Kollektiv

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

An MCP server that provides queryable access to Anti-Money Laundering (AML) red flag knowledge from regulatory documents. It enables compliance officers to ask natural-language questions and receive relevant, sourced red flags from a local vector database.

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

MCP server for Vectros, a typed multi-tenant record store with hybrid search and citation-grounded RAG, enabling agents to query, search, and ask questions over their own indexed data.

A Model Context Protocol (MCP) server that enables LLMs to interact directly the documents that they have on-disk through agentic RAG and hybrid search in LanceDB. Ask LLMs questions about the dataset as a whole or about specific documents.

This MCP server provides evidence-based advice on vector database backends by retrieving measured benchmarks and operational traps, enabling you to ask questions and compare backends through natural language.

Exposes a markdown knowledge base to MCP clients so they can search pages, fetch individual documents, and ask grounded questions that come back with numbered citations or a refusal. Retrieval is graded before answering, with a single query rewrite before giving up when nothing relevant is found.

Enables RAG-based querying of local stock company data using a local LLM and vector database, providing tools to ask questions, search raw chunks, and list documents.

An MCP server that enables searching and retrieving ACL NLP conference papers from a Qdrant vector database using semantic search and structured filters like year, venue, and field of study.

Enables AI agents to interact with an embedded graph database (GrafeoDB) via the Model Context Protocol, providing tools for graph CRUD, GQL queries, full-text and vector search, and graph algorithms.

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.

Provides persistent memory for AI coding agents via MCP, enabling teams to share and recall facts across sessions. Automatically captures, classifies, and curates knowledge from supported transcript sources.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.

A local MCP server that provides semantic code search for Python codebases using tree-sitter for chunking and LanceDB for vector storage. It enables natural language queries to find relevant code snippets based on meaning rather than just text matching.