- 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.
Rag Eval MCP
Touchstone — know if you broke your RAG. An MCP server and CLI that score retrieval quality against a golden set: recall@k, MRR and hit rate, with no LLM calls.
Mycelia
🧠 Long-term memory for AI coding agents — switch tools or models without starting over. Local-first, shared across Claude Code / Codex / opencode via MCP.
Operational Data Platform For AI
Guides and reference architectures for building production AI agents on Couchbase: agent memory, MCP, hybrid retrieval, cloud-to-edge.
Synapse Memory MCP
Synapse: a local-first, private Universal AI Memory layer exposed over the Model Context Protocol (MCP). Gives any AI client persistent, semantic, cross-tool memory via stdio and…
Naeth
Naeth: portable, append-only memory for AI agents, exposed over the Model Context Protocol. Postgres + pgvector, hybrid retrieval, verifiable authorship. Running in production.
Cistern
A semantic cache for LLM calls: collapses paraphrased and reformatted prompts into one cached answer. On realistic agent traffic a byte-exact cache leaks (46% hit rate); Cistern r…
Procureguard AI
Synthetic enterprise procurement copilot benchmarking RAG, vector search, DeepSeek, MCP tools, and guarded human approval
Kopeng
Persistent, self-curating memory for coding agents. MCP tools + REST API, 100% local inference, with an autonomous nightly consolidation pass that collapses duplicates, decays sta…
Tyamka
Local-first, LLM-curated personal knowledge base + Claude Code plugin: research topics, compile cited articles, and query with hybrid retrieval — on your Claude subscription or an…
Hybrid Rag MCP
Self-hosted RAG service exposed over MCP: hybrid retrieval (BM25 + kNN, RRF fusion) on OpenSearch, multi-provider embeddings, Python 3.11, mypy strict
Roowet Semantic Vault Search
Local RAG semantic search for Obsidian vaults — Ollama + LanceDB + MCP. Search your markdown vault by meaning, not keyword.
Powerbrain
🧠 Open-source context engine that feeds AI agents with policy-compliant enterprise knowledge. MCP-native, GDPR & EU AI Act ready, self-hosted.
Synapto
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP
Iris AgenticAI
🤖 Agentic AI Platform with InterSystems IRIS | 🔀 Multi-agent workflows with OpenAI Agents SDK & agent handoffs | 🧠 IRIS Vector Search & RAG | 🌐 MCP Server integration | 🔍 Agent tr…
Stratafs
A semantic filesystem that transforms passive file storage into an intelligent, searchable knowledge base.
Searching Apple Notes
Search Apple Notes semantically with Claude Code. BGE-M3 embeddings, ChromaDB, fully local. Drop-in skill — no MCP setup, no API keys.
Bigrack.dev
BigRack.dev - Intelligent MCP server for task/project & context management in AI development tools
Localvectordb
Document-first sqlite3+faiss vector database
OpenLMlib
Cross-project knowledge library for LLM agents with semantic retrieval, citation-aware quality checks, and safe MCP tool integration
Mnemosyne AI Memory
Bionic memory for AI agents: GraphRAG, predictive memory, dream consolidation, governed skill evolution, MCP, REST API, and dashboard.
Stromadb
Real-time GraphRAG engine optimized for LLMs — stream-native graph + vector + typed retrieval (Rust). Source-available.
Vecgrep
grep using meaning and similarity instead of keywords - local/self-hosted, multimodal, and runnable on any user-defined corpus
Knowledge Master
Local-first knowledge graph for developers. Graph-native RAG with MCP server, blast radius analysis, convention enforcement. Your AI agent's permanent memory.
Braincell
Local-first memory platform for your projects — private per-Project memory, hybrid semantic + keyword recall, and a native Memory Map desktop app. Connects to Claude Code, Codex,…
Memayu
Lightweight, self-hosted-first AI agent memory engine in Rust single binary.
Fgraph
A fact graph in a single SQLite file — embedded temporal fact store with time travel, provenance, hybrid search, and MCP for AI agents
Companybrain
The open-source memory layer for your company. Index everything, recall anything, own all of it.
ResearchBrain
Windows-first、local-first AI 科研文献工作台：支持 Zotero 增量同步、DOI/开放 PDF 获取、MinerU/PyMuPDF 解析、MiniMax 向量化、混合检索、DeepSeek 证据问答、在线文献发现、引用导出与 MCP 集成，无需 WSL、Docker 或 PostgreSQL。
Pi Zgrep
Semantic code search for the pi coding agent. One tool, four routes (hybrid, BM25, vector, ripgrep), auto-indexed. Powered by zg.
Ecommerce AI Agents
A runnable companion to the blog post *"Building E-commerce AI Agents on MongoDB."* A CrewAI shopping agent backed by MongoDB Vector Search, atomic inventory checkout with Change…
Commonmind
Universal memory for human and agent teamwork — transactional, distributed, built on CockroachDB and AWS serverless.
Eaves
Local-first desktop app for multi-agent AI conversations with persistent memory. Your agents, your keys, your data — on your own machine.
Recall AI
Build and manage AI-driven workspaces using Next.js, React, and TypeScript with customizable UI and MIT licensing.
Pigeon Evals
A End-To-End RAG Pipeline that includes Evaluations, iterations, and swappable components. At its core it allows users to be able to try different embedding models and techniques.
Code MCP Tools
Local-first MCP server and web panel for agent memory, project docs, bugs, todos, and RAG search
Wyrd
Semantic search, knowledge graphs, and MCP integration let AI assistants like Claude draw context from your personal ebook library with full source traceability.
TheUltimateRAG
TheUltimateRAG is a production-ready, modular, and highly flexible Retrieval-Augmented Generation (RAG) boilerplate. Built with FastAPI, LangChain, and ChromaDB, it is designed to…
Ecomm Assistant
Agentic RAG e-commerce assistant with self-grading retrieval and web-search fallback — LangGraph, MCP, AstraDB, FastAPI, EKS
Athlete Performance Platform Showcase
Technical showcase production application demonstrating LLM integration, MCP pattern, RAG systems, and modern architecture.
Enhanced Memory MCP
A high-performance memory management system for AI agents using SQLite with zlib compression. Designed for the agentic scaffolding needs of cascading orchestration systems.
Axel
AxelR8 — Portable Agent Intelligence. Search, memory, session awareness in one .r8 file.
Octopus Scout
Octoryn Web Ingestion Engine: governed, auditable, AI-native web/PDF ingestion
PitchCraft Agent
AI agent that flags ticket-resale scams — Gemini + Google ADK grounded in MongoDB Atlas Vector Search + the MongoDB MCP server. Google Cloud Rapid Agent Hackathon (MongoDB track).
Knowledge Forge
Local-first AI knowledge base desktop app: PDF/DOCX/image ingestion, OCR, chunking, embedding, LanceDB vector search, MCP access, and optional AnythingLLM sync. Windows EXE packed.
Organism Memory
Local memory layer for AI agents — persistent, searchable memory across sessions without external APIs
Context Library
Open-source MCP context persistence layer for AI sessions. Append-only handoffs, pgvector semantic search, OAuth2 auth. Model-agnostic.
ITL.Braincell
Centralized memory platform for AI agents — REST API, MCP server, PostgreSQL, Weaviate vector search, and Redis cache for semantic context management
Deep Dive Capstone
Codebase Q&A with (path:line) citations — the capstone of a from-scratch AI-engineering series. Built in 8 eval-gated stages (chat → RAG → agents → hardening → production), provid…
Plugmem
Embedded bitemporal memory engine with hybrid retrieval for local-first applications and AI agents — in-process, no server.
YourBrain
Local-first AI memory engine in Rust. Remembers across sessions, auto-resolves conflicting facts, validates answers against a knowledge base, and caches grounded responses. Single…