"Red Hat" matching MCP servers:

MCP server exposing memory search, index, and stats tools for agents, with honesty guards to prevent re-litigation of settled decisions.

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.

MCP server that enables searching a TOTVS Protheus ERP knowledge base using vector similarity and reranking.

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.

RAGX MCP Server enables retrieval-augmented generation with document ingestion, hybrid search, and agentic answering using Claude, exposing tools for querying, searching, and managing documents.

An MCP server that enables AI assistants to directly interact with Elasticsearch for searching, aggregating, and retrieving documents from indices, supporting full-text search, semantic search, and various query modes.

Facilitates semantic analysis of chat conversations through vector embeddings and knowledge graphs, offering tools for semantic search, concept extraction, and conversation pattern analysis.

Enables semantic search over your Cursor IDE chat history by vectorizing prompts and storing them in LanceDB. Provides a Dockerized API to perform vector similarity searches against your chat history.

Enables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation.

A conversational chat interface that uses RAG over a synthetic test corpus and a domain-knowledge corpus, exposing retrieval via MCP.

An MCP server that answers questions over insurance and regulatory documents using retrieval-augmented generation, returning grounded, cited passages via local embeddings and OpenSearch.