MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
claude-memorygithub.com/hiromiogawa/claude-memoryupdated this year
Claude Code 向けの長期記憶システム — セッションを跨いだ記憶をハイブリッド検索（pgvector + pg_bigm）で提供
-
MCP server for knowledge base with Mastra.ai and pgvector
npm MIT -
remembrallmcpgithub.com/cdnsteve/remembrallmcpupdated this year
Persistent knowledge memory layer for AI agents. Rust core, Postgres + pgvector backend, MCP protocol.
npm MIT -
Semantic knowledge graph navigation for Obsidian or markdown vaults using AI-powered vector embeddings and PostgreSQL+pgvector
MIT ★ 26 -
remembrallmcpgithub.com/roboticforce/remembrallmcpupdated this year
Persistent knowledge memory and code dependency graph for AI agents - Rust, Postgres, pgvector, MCP
pypi MIT -
conduitgithub.com/naumanAhmed3/conduitupdated this year
An MCP (Model Context Protocol) server exposing a pgvector hybrid-retrieval engine as tools, resources and prompts over Streamable HTTP.
-
Verifiable shared memory for AI agents and people: atoms with checked source quotes, revisions and review on PostgreSQL + pgvector
pypi AGPL-3.0-only -
Personal intelligence substrate: embeds a markdown vault into pgvector and serves hybrid search to agents over MCP.
-
mememorygithub.com/scott-walker/mememoryupdated this year
Persistent semantic memory for AI agents. MCP server with PostgreSQL + pgvector. All data stays local.
MIT -
Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
pypi MIT ★ 16 -
Ask RFCs, get answers: pgvector-powered semantic search with RFC 2119 normative keyword filtering, exposed as MCP tools for any AI agent
Apache-2.0 -
RAG engine that loads external data with Render Workflows into pgvector and serves cited search over MCP
★ 1 -
Offline knowledge memory for AI agents: Kiwix + Wiki.js + pgvector over MCP and REST. CPU only, no GPU or AVX needed.
AGPL-3.0 ★ 1 -
Shared, curated semantic memory for Claude Code: Go + Postgres/pgvector + Ollama, MCP server and prompt hook, PR ingest from Azure DevOps/GitHub/GitLab.
Apache-2.0 -
pkbgithub.com/JohnPengC/pkbactive
个人知识库：文档/网页 → LLM 提炼（可选原文直存）→ 双索引混合检索 → RAG 问答 + MCP Server 外挂 AI 编程工具 | Java 17 · Spring Boot 3 · Vue 3 · PGvector
MIT -
tribalgithub.com/tribal-memory/tribalupdated this year
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Rust, Postgres + pgvector.
★ 10 -
Full-stack AI website content-gap & FAQ auditor built with Next.js App Router, TypeScript, BullMQ (Redis), PostgreSQL + pgvector RAG, and an MCP server.
NOASSERTION -
Go API and MCP server for Skein, a task tracker for agents, agents’ agents and people. REST and MCP on PostgreSQL with pgvector search.
NOASSERTION -
memforgegithub.com/memforgeai/memforgeupdated this year
The open-source memory layer for AI agents — MCP server backed by PostgreSQL + pgvector + Apache AGE
npm BUSL-1.1 -
kgngithub.com/baobab00/kgnupdated this year
Knowledge graph CLI + MCP server for AI agents — PostgreSQL/pgvector backed with multi-agent task orchestration, conflict detection, and GitHub sync
MIT -
zakargithub.com/tkbrannon/zakarupdated this year
Zakar (זָכַר, 'he remembers') — personal AI memory platform: pgvector + MCP server + REST API. Every AI you use shares the same long-term memory of you.
MIT -
cocoindex-claude-codegithub.com/pkmdev-sec/cocoindex-claude-codeupdated this year
Complete knowledge base system with semantic search for Claude Code CLI. Powered by CocoIndex, PostgreSQL + pgvector, and MCP protocol.
MIT ★ 2 -
Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp
★ 1 -
A high-performance local knowledge system for Claude Code via MCP. PostgreSQL + pgvector + ONNX embeddings. Gives your AI assistant persistent memory across sessions.
MIT ★ 1 -
MCP server for soccer news with RAG (vector embeddings) and sentiment analysis. Uses PostgreSQL+pgvector and local ML models.
-
Layered, self-learning knowledge base for teams, served over the Model Context Protocol. PostgreSQL + pgvector hybrid search, roles, audit log, YAML layer presets.
MIT ★ 1 -
Deterministic code-graph context engine for AI coding agents - PostgreSQL, Apache AGE and pgvector, over MCP and REST
pypi MIT -
java-kotlin-mcp-server-prototypegithub.com/wongi-jeong/java-kotlin-mcp-server-prototypeupdated this year
MCP server for PDF semantic search — drop a PDF in MinIO, it's auto-embedded (Ollama + pgvector) and queryable via hybrid vector+keyword retrieval.
MIT -
🛰️ AI-powered incident investigation platform 🧠 LangGraph multi agent workflow analyzes logs, service health & deployments, 📚 real RAG via pgvector, 🔒 human-approved remediation, all in one 🐳 Docker Compose stack
-
RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)
-
Hybrid semantic + keyword search over every chat you have (WhatsApp, Signal, iMessage, Instagram and more via Beeper), served to self-hosted agents over MCP. Postgres + pgvector.
MIT -
aging-knowledge-graphgithub.com/GiorgioHuang/aging-knowledge-graphupdated this year
An open, evidence-traceable knowledge graph for healthy aging — Postgres + pgvector, REST + MCP API, natural-language search, and Claude-powered curator/reviewer agents.
MIT -
High-performance Technical Knowledge Base & MCP Server powered by PostgreSQL 17, pgvector (HNSW), Lexical Search (GIN), Reciprocal Rank Fusion (RRF), and Automated Technical Entity Graph Extraction.
MIT ★ 2 -
code-review-botgithub.com/SManojna/code-review-botupdated this year
LangGraph ReAct agent that reviews GitHub PRs — fetches diffs, retrieves similar past reviews via pgvector, posts context-aware comments through a custom MCP server, and learns from user feedback. Deployed on Cloud Run.
-
A retrieval engine that refuses to guess. Register git repos and URLs, get grounded, cited answers over MCP and REST. Hybrid search, cross-encoder rerank, Postgres + pgvector.
MIT -
RCLL — self-hosted, hierarchical shared memory for a team of AI agents over MCP (rooms, L0-L3 depth, pgvector). Fork of vectorize-io/hindsight.
npm MIT -
Juntogithub.com/AayushCharde/Juntoupdated this year
Keyboard-first task tracker with a built-in MCP server — manage your tasks from Claude or any MCP client. SvelteKit · Cloudflare Workers · Supabase · pgvector. AGPL-3.0.
AGPL-3.0 -
mnemos-mcpgithub.com/Tanush1912/mnemos-mcpupdated this year
Self hosted MCP knowledge server. Turn docs into searchable context with multi collection isolation, deterministic ingestion, and local vector search via Ollama + pgvector. 100% private, zero vendor lock in.
MIT ★ 2 -
Legal-first scholarly discovery with verified open-access links, persistent research libraries, and MCP tools for AI agents — built with Java/Spring Boot, Next.js, and PostgreSQL/pgvector.
NOASSERTION -
Self-hosted MCP server that gives LLM agents (Claude Code, Claude Desktop) persistent cross-session memory across four CoALA-style layers (Postgres + pgvector + TimescaleDB, Redis).
Apache-2.0 -
Explainable, RAG-based resume ranking against a job description. Spring Boot 3.5 + Spring AI, OpenAI embeddings and pgvector, LLM scoring with strengths, gaps and rationale, also exposed as an MCP server for AI agents.
MIT -
MCP server with 40 tools for web design analysis — layout extraction, motion detection, quality scoring, accessibility audit, Core Web Vitals, design comparison, and semantic search via Playwright, pgvector, ONNX Runtime, and Ollama.
AGPL-3.0 ★ 2 -
Filesystem-first hybrid vector memory engine & MCP server in Go. Couples human notes (Obsidian/Copyparty) with PostgreSQL + pgvector, hybrid RRF search, graveyard safety guardrails, and parent-child chunking for nomic-embed-text-v2-moe.
-
Citation-grounded document memory for AI assistants. Offline, MCP-native RAG server for Claude Desktop, Claude Code & Cursor: every passage comes with file, page and a verbatim quote. pgvector + hybrid search, Turkish-ready.
pypi MIT -
md-managergithub.com/nimeus/md-managerupdated this year
Markdown docs that live in Postgres, built for AI agents — MCP server (Claude.ai / ChatGPT connector + stdio), CLI, and web UI over one multi-tenant, RLS-isolated API. Rust + Axum + Next.js, with pgvector semantic search.
MIT -
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.
MIT ★ 37 -
Arisgithub.com/GilCFP/Arisactive
B2B SaaS that turns sales artifacts (transcripts, PDFs, contracts) into living project context. Time-weighted RAG over pgvector, role-scoped agents, stage-gated lifecycle, BYOK with AES-256, and a standalone MCP server. Next.js 16 · TypeScript · PostgreSQL 17 · Gemini.
-
Production nutrition-tracking PWA (React, Supabase) built and operated inside Claude Code: production RAG pipeline, hybrid semantic search (pgvector), self-built remote MCP server (OAuth 2.1 + PKCE, RLS-enforced), three-model AI fallback chain, and an LLM eval harness gating every release.
MIT -
Git DAG indexing, AST symbol graphs, and hybrid semantic code search MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Maps repositories into PostgreSQL + pgvector with recursive caller/callee dependency graphs and temporal recency decay.
MIT -
Ask a security question in plain English and get the NIST SP 800-53 controls that answer it, each one cited. Measured keyword, vector, and hybrid search with pgvector, cited answers from a local model, a website, and an MCP server for AI assistants.
MIT -
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 memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.
NOASSERTION ★ 1 -
Persistent memory and knowledge graph for AI agents via MCP — PostgreSQL + pgvector + Ollama
MIT ★ 1 -
lore-mcpgithub.com/davidgut1982/lore-mcpupdated this year
Advanced MCP server for unified knowledge management with PostgreSQL+pgvector, knowledge graphs, research workflows, and Claude Code integration
MIT ★ 5 -
Sistema de Memoria Dual MCP con Búsqueda Híbrida (SSC/BIRE) — PostgreSQL + pgvector + pg_trgm + embeddings locales (Ollama)
MIT ★ 5 -
raglike.mdgithub.com/andrecrjr/raglike.mdupdated this year
A high-performance, local semantic search engine for Markdown documentation. Built with Bun, PGlite (pgvector), External Postgres Support, and Xenova Transformers.
-
Autonomous, headless AI Go-to-Market (GTM) outbound engine & MCP Server powered by PostgreSQL 16 + pgvector.
MIT ★ 2 -
Shared memory for AI agents over MCP: one agent contributes what it learned, another one finds it. Seven tools, PostgreSQL with pgvector, PII removal before storage.
MIT ★ 2 -
Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. No cloud required.
MIT ★ 9 -
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector
pypi Apache-2.0 ★ 39