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.
-
preference-memory-mcpgithub.com/efficjump/preference-memory-mcpupdated this year
Local-first MCP server for scoped, reviewable, privacy-conscious preference memory.
Apache-2.0 -
preference-layergithub.com/ethanluh/preference-layerupdated this year
PreferenceLayer is a portable preference infrastructure and API for the agentic web. It empowers AI shopping agents with user-controlled preference credentials (PTP) and profile-conditioned product quality intelligence (QIL) across platform silos. Built with MCP-native bindings to eliminate cold-start friction in agentic commerce.
NOASSERTION ★ 1 -
MCP server for editing Android preferences
npm Apache-2.0 -
Preference Editor MCP server
npm Apache-2.0 ★ 2 -
Ethos protocol for learning, recording, and syncing user tendencies/preferences across all platforms, harnesses, and surfaces.
Apache-2.0 -
Typed preferences that any AI agent can read on your terms, kept in your own browser.
npm MIT -
MCP server for Tableau Knowledge: semantic search, lineage, impact, Business Preferences checks, and semantic-layer porting via Apache Ossie (OSI), from any MCP client.
pypi MIT -
kotauth-mcpgithub.com/InumanSoul/kotauth-mcpupdated this year
Kotauth MCP server, manage your auth server directly from your preferred client
npm MIT -
MPC Server to connect your preferred model with rae-api.com
go ★ 8 -
A task tracker built for AI agents, operated entirely through MCP tools via your preferred AI agent.
npm AGPL-3.0 ★ 1 -
An MCP server for the Libraries Ireland catalogue, to scour for interesting books, preferably in your local branch.
MIT ★ 6 -
Capture macOS system preferences to an auditable TOML file and restore them on a new machine
MIT ★ 1 -
riserflowgithub.com/riserlabs/riserflowupdated this year
Open-source MCP server for AI-powered e-commerce — search, cart, orders, preferences
Apache-2.0 ★ 1 -
memory-mcp-servergithub.com/yossifibrahem/memory-mcp-serverupdated this year
A persistent memory MCP server for LLMs. Models can save facts, preferences, context, and decisions — and recall them across sessions.
-
Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.
Apache-2.0 ★ 4 -
chittagithub.com/ninthhousestudios/chittaupdated this year
Personal cognition store for practitioners and agents — research notes, observations, preferences, working models. Postgres + pgvector, hybrid retrieval, MCP server.
AGPL-3.0 -
sift-releasesgithub.com/edwardedmonds/sift-releasesupdated this year
Persistent memory for Claude Code. Preferences, patterns, and decisions that survive across sessions.
★ 2 -
attio-simple-mcp-servergithub.com/mlemos/attio-simple-mcp-serverupdated this year
A very simple MCP server for Attio CRM - a starting point if you want to integrate Attio with your preferred AI tools
★ 1 -
MCP server to read and manage a three.ws notification inbox, delivery preferences and Web Push devices.
Apache-2.0 ★ 9 -
Control your Philips Hue lights with AI. MCP server for setting vibes, saving favorites, and learning your lighting preferences.
npm MIT -
touch-grass-mcpgithub.com/AG-Dynamics-GH/touch-grass-mcpupdated this year
Preference-aware events discovery MCP server. Knows what you like, surfaces what you'd actually want to do.
MIT ★ 1 -
tplink-omada-mcpgithub.com/MiguelTVMS/tplink-omada-mcpupdated this year
MCP server for TP-Link Omada Controller. Use your prefered AI agent to see all the information on your TP-Link Omada Controller.
MIT ★ 29 -
tdai-mcp-servergithub.com/iceyychain/tdai-mcp-serverupdated this year
A MCP tool designed for agents like TRAE and other popular ones, which can help the agent to memorize conversations with user and summarize his/her preferences.
★ 2 -
everything-jet-plugingithub.com/0xABADBABE-ops/everything-jet-pluginupdated this year
The world's first Everything MCP plugin. Use your AI Agent (Qwen Code preferred) to chat with everything (pun intended) stored across your drives.
MIT -
Open, MCP-native training-data foundry: turn permitted documents into traceable, quality-gated SFT and preference datasets.
Apache-2.0 ★ 1 -
A local Rust MCP server with communication tools, prompts and skills for neurodivergent users. Preserves meaning, respects preferences and keeps processing on your device.
MIT ★ 1 -
Long-term memory for Claude Code, Codex and other MCP agents: your preferences, rules and context, shared across agents and machines. Self-hosted.
Apache-2.0 ★ 1 -
Local-first memory for AI assistants. Keep preferences, decisions and lessons across sessions and connected tools in readable Markdown files.
npm MIT ★ 12 -
UserContextMCPServergithub.com/HappyMonkeyAI/UserContextMCPServerupdated this year
A local **stdio Model Context Protocol (MCP) server** that exposes a developer's local context (communication preferences, development stack, active repositories, memory models) to AI agents.
MIT -
Local-first AI planner that learns your preferences and turns events into memories. Your data stays on your machine.
AGPL-3.0 -
memexgithub.com/kioie/memexactive
Long-term memory for AI coding agents — local MCP server for Cursor & Claude. Remember preferences across chats on your machine. No cloud, no API keys. Go + SQLite.
oci MIT ★ 1 -
project-guide-agentgithub.com/anthropics/project-guide-agentupdated this year
Context-aware, memory-driven developer assistant with Jira + Git integration, smart ticket guidance, persistent preferences, and intelligent workflow automation
npm ISC -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio in blinded pairwise preference or human-vs-AI detection studies.
pypi MIT -
Universal local-first persistent memory for AI coding agents. Remember project context, technical decisions, debugging solutions, and developer preferences across sessions.
MIT -
FileAsist, a file organization agent running on small language model, on your local, reading you files, understanding them and organizing it based on your preferences.
★ 1 -
Varyz plugin for Claude: bring your saved preferences and approved project history into Claude.
AGPL-3.0 -
cerberus-mcpgithub.com/proxikal/cerberus-mcpupdated this year
MCP server for AI agents: intelligent code exploration (AST-based symbol search, architectural blueprints, call graphs, 90%+ token reduction) + persistent session memory (global preferences, project decisions)
-
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
npm MIT ★ 62 -
🔥🖥️ MCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations.
★ 170 -
Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zero-dependency, local-first, 85% PrefEval accuracy.
pypi MIT ★ 9 -
A zero-dependency SQLite memory layer for AI agents that learns what works: patterns graduate to proven preferences via a built-in experiment loop.
pypi MIT -
Persistent Knowledge Graph Memory for AI Coding Agents. Adds long-term context (goals, strategies, preferences) to Cursor, Windsurf, & VS Code via MCP.
pypi MIT ★ 16 -
Shared long-term memory as a knowledge-graph MCP server — persistent context, preferences and project knowledge for Claude Code, opencode and any MCP-capable AI agent.
MIT ★ 5 -
A zero-dependency SQLite memory layer for AI agents that learns what works: patterns graduate to proven preferences via a built-in experiment loop.
pypi MIT -
myndgithub.com/oxHive/myndactive
Persistent memory MCP server for AI coding agents. Injects project context at session start, stores architectural decisions, and recalls preferences works with Claude Code, Cursor, Windsurf, OpenCode, Kimi, and Codex.
npm AGPL-3.0 ★ 2 -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio blind (pairwise preference or human-vs-AI detection). Not MOS.
pypi MIT -
Un serveur MCP qui réunit recherche de CV (Qdrant), wiki de règles et mémoire des préférences, avec un agent local mesuré sur le choix des outils.
MIT -
claudebot-memorygithub.com/solan/claudebotupdated this year
MCP Server for persistent bot memory — stores learnings, preferences, skills and workflows in a local JSON store. Works with any MCP-compatible client (Claude Code, Claude Desktop, Cursor, etc.)
npm MIT -
remember-mcpgithub.com/prmichaelsen/remember-mcpupdated this year
Store, search, and retrieve memories with semantic and keyword search. Create relationships between memories to build knowledge graphs. Organize with tags, types, and trust levels. Publish memories to shared spaces and manage user preferences for intelligent context retention.
npm ★ 2 -
A MCP server that bridges AI agents to the macOS desktop: the accessibility tree, synthetic mouse and keyboard input, screenshots, window and application control, the shell, preferences, launchd, processes, the filesystem and web scraping.
go MIT -
Give the AIs you authorize a long-term memory with evidence. Explain decisions, preferences and lessons once, and get them back later with their source and history.
-
grounded-code-mcpgithub.com/michaelalber/grounded-code-mcpupdated this year
Ground your AI coding agent in the books, standards, and docs you actually trust. A local MCP RAG server that makes your preferences the default.
MIT -
MCP server that personalizes LLM replies for ChatGPT, Claude and Grok. A reinforcement learning bandit learns each user's preferred length and format in real time, with A/B testing to measure impact. Live at claire.pm.
-
context-scribegithub.com/Joaolfelicio/context-scribeupdated this year
A Persistent Secretary for AI agents that autonomously extracts rules and preferences from chat logs and syncs them to your Memory Bank via MCP. Eliminate Agent Amnesia.
Apache-2.0 ★ 1 -
Local-first memory for AI agents. Structured synthetic memory cards (decision / preference / risk) with verifiable state history via ERC-8350. Offline, no account. MCP + 7 agent runtimes.
pypi MIT ★ 12 -
Open-source trip-planning MCP service: plans, preferences and changes kept in your own private Git repo; self-hosted with Docker or Railway (旅行规划 MCP 服务,自己部署)
MIT -
Stop reintroducing yourself to AI. An open protocol for portable user preferences and context across Claude, Cursor, Windsurf, Codex, Gemini and any AGENTS.md agent. MCP server + CLI.
npm MIT ★ 4 -
Remember MCP, the VS Code extension that brings real, persistent memory to your AI assistant and your team. Instantly store preferences, facts, and best practices—so Copilot always knows your context, and your team’s knowledge is never lost.
MIT ★ 8 -
MemoryMeshgithub.com/0DevDutt0/MemoryMeshupdated this year
Production-grade persistent memory server for AI agents. MCP-compatible (Claude Code, Cursor). Four memory types (episodic/semantic/procedural/preference), hybrid vector retrieval (FAISS + bge-large), hierarchical LLM compression (Groq + Mistral), Ebbinghaus forgetting curve, FastAPI + Streamlit.
-
The accessibility layer for AI coding agents, WCAG 2.2: static and rendered audits (light AND dark), contrast over images, blindfold usability testing, PDF/DOCX screening, caption quality, prefers-reduced-motion audit, evidence packs a human can sign. Zero deps
npm MIT ★ 7