- Conduid
- Marketplace
- #vector-search
MCP servers tagged vector-search
546 live MCP servers tagged "vector-search", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vector-search.
Zelatix V2
Zelatix v2: Agent-Native Context Database
Embedmind
Persistent memory for AI agents — one local file, fast, no server. Vector + full-text + graph, via MCP + CLI. Built in Rust.
Supabase Vector Gmailkb Rag
📬 Deterministic & programmatic Gmail → Supabase → Crawl4AI vector knowledge base for UC Berkeley MIDS.
MCPARDF CLIENT
Cliente MCP (TypeScript + Express) que sincroniza catálogos ARDF, indexa en SQLite (sqlite-vec) y expone búsqueda híbrida (semántica+léxica) vía API REST ( /status, /sync, /refres…
Visioneer
Autonomous AI agent with multi-layer memory, MCP servers, and Claude API. Set a goal, it researches, plans, and executes.
Sgcp Rag
Self-correcting, SNI-guided RAG (SGCP-RAG) with LangGraph, pgvector, and MCP integration
Microsoft Learn MCP Server
Microsoft documentation MCP access
Deeplore
Self-hosted RAG-powered knowledge base built for depth, served over MCP.
EliteDangerousKB
Autonomous, self-verifying Elite Dangerous knowledge engine + local RAG copilot (COVAS). Grounded-only answers, 100% local inference, built by an AI council.
Pack AI
AI and LLM integration skills with RAG, embeddings, and vector search
Prx Memory
Local-first MCP memory component for coding agents. Store, recall, evolve.
Docmind MCP
Semantic document retrieval system, exposed via MCP, for AI agents like Claude
Findyourcode
search a codebase by what the code does, not the words in it. tree-sitter chunking, hybrid vector + bm25 retrieval, one sqlite file, offline.
Fayna Rag MCP
Local knowledge base with RAG and MCP server
Brain.db
Persistent memory database for MCP systems — SQLite, FTS5 search, vector embeddings, 3-signal RRF recall, ACT-R decay, graph edges. (Companion repo — architecture and interface on…
Topk
Topk — independent third-party profile of a public API surface, by API Evangelist. TopK is a search engine for accuracy-critical AI applications, delivering hybrid search, multi-v…
Ticket Rag
Hybrid MCP + RAG system for querying and summarizing GitHub issues using local LLMs, vector search, and semantic routing via Ollama. Capability Highlight: Demonstrates hybrid AI…
Kbsearch
MCP server for semantic knowledge base search using LlamaIndex embeddings. Auto-ingests from S3, vector search with configurable chunking.
Kybase
Self-hosted persistent memory for AI agents. Markdown for humans, MCP for agents.
Mnemon Memory MCP
Persistent layered memory MCP server for AI agents — SQLite + FTS5 + vector hybrid search (RRF), multilingual, zero-cloud
Virtual Engineer
AI-assisted chiller troubleshooting demo powered by MongoDB Atlas, MCP tools, and an LLM agent with real-time retrieval transparency.
Docs Assistant
Agentic RAG assistant for the MCP TypeScript SDK — version-correct (v1/v2), cited answers that refuse when the docs don't cover it. Next.js + AI SDK + LangGraph + pgvector.
Give Obsidian A Memory
Claude forgets you. Your notes don't. — Local memory for Claude, built on Obsidian + Ollama. One-file installer for macOS / Windows / Linux.
Mint Mory
Typed, graph-linked, self-consolidating memory for LLM agents — single-file SQLite, with MCP/CLI/HTTP. ’Member or die!
Openai Study Mode Clone
An intelligent AI tutoring system that uses Socratic teaching methods to guide students through personalized learning experiences. Built with OpenAI Agents SDK and Google Gemini,…
SEC RAG MCP
MCP server with a RAG pipeline over SEC EDGAR 10-K filings: section-aware chunking, BGE embeddings, ChromaDB, Loughran-McDonald sentiment, and year-over-year filing comparison.
Book Brain
A GBrain-shaped knowledge brain over open-source / free books. Markdown on disk, SQLite + sqlite-vec hybrid search, typed graph edges, MCP server. TypeScript on Node + tsx, Ollama…
Aingle
The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.
Local Knowledge Rag MCP
A semantic search and retrieval system for local documents using vector embeddings. Powered by MCP (Model Context Protocol).
Vaultspec Rag
Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.
Ollqd
📚 Index codebases and docs into Qdrant with Ollama embeddings, enabling AI assistants to search code via Model Context Protocol (MCP).
Brain Rag
Hybrid retrieval-augmented search over a corpus of markdown files. Vector and keyword search fused into one ranking, optionally reranked by a cross-encoder, served locally over a…
Picoqmd
Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.
Obsidian MCP Semantic Metagraph
Obsidian MCP-RAG server for AI agents [Local & Cloud] with full-note, heading-aware semantic retrieval, lexical search, graph navigation, passage provenance, and vault manipulatio…
Mdya
Small, fast retrieval primitive for local Markdown — FTS + on-device vector search + MCP server. local-first, no cloud.
Duxxdb
The database built for AI agents - hybrid vector + BM25 + structured, durable, with RESP / MCP / gRPC servers. Apache 2.0.
Homebrew Amanmcp
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
Fridai
A local MCP server that lets AI coding agents recall your code, commits, and conversations.
Engraphy
An MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a mem…
Knowledgebase Service
Connective tissue for a GitHub account: a reusable knowledge API + MCP server mapping repos, dependencies, and the agents/people working across them. Demonstrated on my own accoun…
Hf Data Agent
Internal RAG data agent with shared UI/MCP/Slack entrypoints, live data tools, and Hugging Face model backends.
Pinakes
Pinakes — a portable, agent-first knowledge base. One directory = one KB.
Grepmem
Vectorless agent memory. HTML storage + grep retrieval. LongMemEval-S R@5 = 98.9%. No embedding, no vector DB.
Kaos Ast
High-precision code context provider for AI agents. Bridges code_ast parsing with cocoindex-code for semantic chunking and local vector embeddings
Indox
Hybrid search across code and docs, served as an MCP endpoint. Self-hostable.
Akopia
Plug. Sync. Serve. — headless retrieval plane for your AI stack. Self-hosted RAG infra with Qdrant + Meilisearch + Redis, plugin-first, MCP-native.
Flashback
Dynamic episodic memory for LLMs. Self-hosted Rust microservice. Vector index + temporal graph + tiered retrieval + REST/MCP.
Cube Memory SDK
Persistent AI memory with crossover — your AI at home shares the same memory as your AI at work. What one LLM learns, all your AIs know. Memory + PKM for Claude, GPT, Gemini & loc…
Contextcortex
High-performance Model Context Protocol (MCP) server providing syntax-aware Code RAG, hybrid retrieval (Dense + BM25), Tree-sitter AST chunking, and multi-repo Git indexing.
Codesage
Graph-Augmented Code Intelligence RAG engine pairing deterministic AST call graphs with dense vector search to boost direct-callee Recall@8 from 0.0% to 53.3% (+53.3 pp) under a 5…