"Understanding RAG (Retrieval-Augmented Generation or related topics)" matching MCP servers:

RAG Vault lets your AI coding assistant search your private documents locally. Everything runs on your machine and your data stays private.

Agentic RAG Knowledge Assistant is a secure, tenant-isolated MCP server built with FastAPI, PostgreSQL, and pgvector that enables document ingestion, semantic retrieval, and vector search over PDF, DOCX, and text files through authenticated MCP tools.

A privacy-preserving local RAG system integrated with MCP, enabling natural language queries over ingested documents and a SQLite database through vector search and local database tools.

Connects to a PostgreSQL database (pgvector) to perform semantic retrieval via the search_documents tool, returning raw document snippets for LLM synthesis.

Read-only MCP server that exposes ZAP's RAG search modes (plain, hybrid, hybrid_rerank) for agents to perform semantic code retrieval.

Enables RAG (Retrieval-Augmented Generation) with tools for vector search, document access, and OpenAI integration, plus MySQL storage and file system operations via MCP.

Enables AI assistants to search NHTSA recall documents and query governed dbt analytics via validated, read-only text-to-SQL, returning citable evidence and data freshness without granting database or file access.

Enables semantic search and retrieval of code files using embeddings stored in PostgreSQL. Supports intelligent codebase exploration through natural language queries, file listing, and content retrieval.

A private MCP server that converts natural-language questions into embeddings and performs semantic retrieval over document chunks stored in BigQuery, returning structured passages with source and page metadata. It serves as the read-only retrieval layer for a document-grounded chatbot.

Enables read-only document retrieval and SQLite exploration through tools over stdio, enforcing a safety gate before SQL execution.

A comprehensive Model Context Protocol (MCP) server providing advanced access to the UniProt protein database.

A Model Context Protocol server for reading TiDB RAG knowledge base, enabling browsing, searching, and vector search of knowledge entries.

Enables natural language queries to a company database through the Model Context Protocol, with read-only enforcement and agentic error recovery.

Enables retrieval of tutor lesson scripts from Supabase and diarized transcripts from PencilSpaces, with Google OAuth gating to a domain.

Stores Organizations content

A powerful AI service platform that provides complete MCP tool calling capabilities and RAG knowledge base functionality, enabling users to connect to multiple MCP servers and perform intelligent document search.

MCP server platform enabling agents to self-register and access geo MCP tools (read-only geo_entities) plus hello ping services via a public MCP endpoint.

Enables AI copilots to understand and query Salesforce org configurations through intelligent metadata chunking and semantic search. Provides access to Apex classes, custom objects, flows, layouts, and other metadata with hybrid vector and keyword search capabilities.

Enables a unified AI assistant that combines document retrieval (RAG), database queries via MCP tools, and web search, allowing users to ask complex questions and receive answers from multiple enterprise sources.

Enables querying a Neo4j knowledge graph about Wroclaw University of Science and Technology using natural language. Converts user questions into Cypher queries and retrieves contextual information through an intelligent RAG pipeline with LLM-powered query routing.

MCP server for managing and retrieving reusable SQL templates with semantic search, enabling a workflow of generation, retrieval, and templating.

A production-grade MCP server demonstrating the wrapping pattern for AI-augmented data pipelines, specifically a job-search scoring pipeline.

Enables secure role-based querying of company documents across different departments (Engineering, Finance, HR, Marketing) with access control that restricts data visibility based on user roles. Provides retrieval-augmented generation with source citations and metadata for trusted corporate knowledge access.

Enables interaction with self-hosted LLM models via Ollama and Supabase database operations. Supports text generation, SQL queries, and data storage/retrieval through natural language commands.

Integrates Snowflake Cortex AI features like Cortex Search and Analyst into the MCP ecosystem, enabling retrieval-augmented generation and structured data analysis. It also provides tools for chat completions and agentic orchestration using Snowflake-hosted large language models.

Read-only MCP server connecting Codex to Neo4j for querying projects, clients, tasks, and SEO audit results.

Automatically routes natural language questions to RAG or Text2SQL paths to answer queries about virtual construction site data, supporting semantic search and structured aggregation.

Enables LLM-based agents and MCP-compatible clients to perform full CRUD operations on FHIR resources, process documents, run semantic searches, resolve LOINC terminology, and query or manipulate clinical data through natural-language prompts. It provides a standardized interface to connect with FHIR-compliant backends and RAG-ready document retrieval.

Enables enterprise SaaS support teams to get retrieval-augmented answers from indexed support documentation and to run natural-language questions as SQL queries against a support PostgreSQL database. It returns answers with source references and exposes the generated SQL alongside its results, with optional tracing and evaluation.

Enables PostgreSQL querying and schema retrieval, NLP/LLM intent classification and SQL generation, tool-intent resolution, and file listing through MCP tools.