Vector and RAG MCP Servers
Vector stores and retrieval pipelines for grounding answers in your own documents. 197 servers in the registry match this topic; 7 of the top ones are answering right now, exposing 207 tools between them. Checked every 15 minutes.
197 in this topic 7 of the top answering checked every 15 min
Ranked by uptime and installs
how the ranking worksNVIDIA 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.
Easy-to-setup local RAG server with minimal configuration
Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Associative key-graph memory for LLM agents — recall by association, not vector similarity.
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Deep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.
Historical chart-pattern intelligence for AI agents. 25M+ embeddings, 19K+ symbols, 10y history.
Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Ingest and analyze Terraform modules from multiple repositories for AI RAG systems
Web scraping, browser automation, vision, OCR, audio, RAG — 9 MCP tools via Arachne API
Semantic document memory using Redis vector store. Save and recall files with natural language.
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.
Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Read-only Qdrant vector DB for AI agents — collections, info, browse points, count, search.
MCP server for Forge, Voxell's hosted text-embedding API. Tools: embed and list_models.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
rag-knowledge-mcp MCP server by MEOK AI Labs
rag-knowledge-graph-mcp MCP server by MEOK AI Labs
Ingest, manage, and retrieve documents for RAG-powered AI applications
Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
MCP server for converting bitmap images to SVG vector graphics using potrace tracing.
130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.
Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.
Hosted DNA language models: promoter, splice, enhancer, chromatin, expression, annotation
Korean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas.
India's financial MCP — Indian cards, loans, FDs, MFs; EMI/SIP/tax calcs; NSE/BSE quotes; RAG.