Vector and RAG MCP Servers
Vector stores and retrieval pipelines for grounding answers in your own documents. 375 servers in the registry match this topic; 9 of the top ones are answering right now, exposing 75 tools between them. Checked every 15 minutes.
375 in this topic 9 of the top answering checked every 15 min
Ranked by uptime and installs
how the ranking worksAutonomous AI video editor over MCP: viral clips, captions, reframe, chroma key, MP4 export
Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Persistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Easy-to-setup local RAG server with minimal configuration
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Deterministic evidence about embedding spaces and vector indexes: hubness, collapse, ANN recall
The full Qdrant API as 58 MCP tools: plain-text semantic/BM25/hybrid search and a search advisor.
Offline, read-only tools that verify AI claims against evidence and replay conformance vectors.
Knowledge-graph RAG for multi-language codebases: index, query and edit code in natural language.
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.
Recall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.
Shared Graph-RAG memory for AI agents: markdown vault, wikilink recall, tasks, messaging.
Scans RAG content/scraped pages for indirect prompt injection
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Create and edit PDFs: text, Markdown, tables, metadata and pages, with Japanese font embedding.
Web design analysis with 26 MCP tools: layout, motion, quality, semantic search via pgvector
Search self-contained .pikelet knowledge artifacts over MCP — no vector DB, no embedding API.
Vectorless, structure-first search over large Markdown libraries: section trees + zh/en BM25
Ask, compare and judge 33 Bedrock text models, generate and edit images, plus video and embeddings.
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Convert .eml and .mbox email to clean Markdown for RAG, LLM pipelines, and local knowledge bases
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Model Context Protocol server for the VectorMethods VideoVector media intelligence API.
Local AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed.
Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.
Self-hosted web search for AI agents — zero API keys, embedding rerank, multi engine parallel search
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
Local RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.
Store and retrieve text in a Qdrant vector database by similarity search.