Vector and RAG MCP Servers
Vector stores and retrieval pipelines for grounding answers in your own documents. 257 servers in the registry match this topic; 5 of the top ones are answering right now, exposing 34 tools between them. Checked every 15 minutes.
257 in this topic 5 of the top answering checked every 15 min
Ranked by uptime and installs
how the ranking worksEasy-to-setup local RAG server with minimal configuration
Local multi-client RAG server over the Model Context Protocol.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Deep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.
PowerPoint (.pptx) MCP server: editable vector diagrams, tables, budgeted reads, render-to-verify
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.
MCP server that wraps the Qdrant vector database API as tools.
Full-text Asian financial reports (China, Korea, Japan, Taiwan) as clean Markdown for RAG agents.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access
Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Create and edit PDFs: text, Markdown, tables, metadata and pages, with Japanese font embedding.
Associative key-graph memory for LLM agents — recall by association, not vector similarity.
MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.
Local-first RAG engine with MCP server for AI agent integration.
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.
Ingest and analyze Terraform modules from multiple repositories for AI RAG systems
Ingest, manage, and retrieve documents for RAG-powered AI applications
Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.
Search the web, generate AI responses, and create embeddings with real-time information
Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.
Create and manage vector database indexes, backups, and collections
Search self-contained .pikelet knowledge artifacts over MCP — no vector DB, no embedding API.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Arachne MCP — scraping, browser, vision, OCR, RAG, Social Research, GitHub + VRT (56 tools).
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Semantic document memory using Redis vector store. Save and recall files with natural language.
Rag Knowledge Graph MCP Server by MEOK AI Labs
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
Run WhatsApp AI agents: manage agents, conversations, CRM contacts, orders and RAG docs.
Rag Knowledge MCP Server by MEOK AI Labs
Convert .eml email exports to clean Markdown for RAG, LLM pipelines, and local knowledge bases