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.
-
Vibe learn anything: your AI agent turns an article, doc, or code into a short interactive lesson with a shareable link.
Apache-2.0 ★ 6 -
Murphys Law — a lessons-learned register for AI agent fleets. Whatever can go wrong, will — once. MCP server + CLI.
MIT -
Give your agent the lessons other agents already learned: one-sentence lessons, must-dos and must-nots by stack and situation, read before a task, left after. MCP client for agents.mightys.dev.
npm MIT -
Learn the Greek hiding in everyday English, in 3-minute lessons. Web app + MCP server so your AI agent can tutor you.
MIT ★ 5 -
Language-learning coach MCP server for Claude Code: Claude writes the lessons, LangCoach keeps your weekly plan, streak, XP and spaced-repetition (FSRS) reviews on your machine.
npm MIT -
Learn what you don't know yet from the code your AI agent writes. Free and secure by design, for Claude Code, Claude Desktop, Gemini CLI & Codex — one lesson at a time.
npm AGPL-3.0 ★ 5 -
Long-term memory MCP server for OpenCode and other harnesses — stores preferences, lessons, and usage history in a single local SQLite file (100% local, no external API) so the AI can "remember and adapt" to the user through context-based learning.
npm MIT ★ 3 -
One MCP gateway that gives AI agents a real browser and a memory per website: lessons, fixes and the site's internal API, learned from real traffic
MIT -
Seamark helps AI coding agents stop repeating mistakes by learning from Git history and code reviews. Repository lessons, MCP tools, and agent skills.
Apache-2.0 -
Co-Learn with your Agent: official remote MCP server for Apex AI Academy, with fact-checked AI lessons in Human and Agent views. Endpoint: https://apexai.academy/mcp
MIT -
This demo showcases a simple MCP example that downloads files from Arxiv and produces some insights from that. Taken from this coursera course: `https://learn.deeplearning.ai/courses/mcp-build-rich-context-ai-apps-with-anthropic/lesson/dbabg/creating-an-mcp-server`.
-
Self-learning memory for AI agents — experience captured automatically, distilled into lessons overnight, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, and Pi.
npm NOASSERTION ★ 3 -
MCP server that centralizes institutional coding rules and lessons learned, serving only the scope-relevant slice to AI agents instead of full-file reads. AI Master's capstone project.
pypi Apache-2.0 -
recall-memory-mcpgithub.com/ashleyevz89-hue/recall-memory-mcpupdated this year
Relevance-gated, self-improving procedural memory for AI agents, as an MCP server. Loads only the lessons relevant to the task, learns from failures, prunes what it never uses. ~99% less context per task.
MIT -
swarm-marketgithub.com/LeSingh1/swarm-marketupdated this year
🏆 1st place (Audience Favorite), Beta Fund x EverMind Hackathon 2026. The app store for agent experience: agents publish learned skill-packs to a shared EverMind-backed registry and install each other's lessons in one call. MCP-native.
-
claude-mcp-coursegithub.com/jaygaha/claude-mcp-courseupdated this year
A hands-on learning path for the Model Context Protocol (MCP) featuring structured lessons on server construction, client implementation, and the three MCP primitives (Tools, Resources, Prompts), accompanied by a fully working CLI chat demo project (documentMCP) that integrates Claude with an in-memory document store.
★ 1 -
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
MIT ★ 3 -
Your AI agent remembers every Little Language Lessons lesson: memory, weekly plan, FSRS reviews and streaks, on your own computer. No API key.
npm MIT ★ 1 -
learn-anythinggithub.com/PranayMahendrakar/learn-anythingupdated this year
Turns any topic into a real lesson - prerequisites, intuition, worked example, misconceptions, practice and spaced repetition. Free MCP plugin for Claude and ChatGPT, zero extra credits.
MIT -
Open-source, self-hostable platform for interactive lessons — Duolingo-style languages and Brilliant-style science & math, made by people and AI agents (MCP, BYOK AI).
AGPL-3.0 -
AI chatbot orchestrator — personas, safety-guarded conversations, TTS, VRM avatar, structured language lessons (any language, deep Japanese/JLPT)
MIT ★ 1 -
CLI + MCP server for italki — search teachers, compare, read reviews, check schedule, and track lessons from the terminal or AI tools
★ 1 -
openclaw-hackathongithub.com/Trolleroof/openclaw-hackathonupdated this year
Apollo Labs RL run orchestrator: FastAPI PPO training, eval baselines, rollout GIFs, canonical RunReports, AgentMail delivery, Nia lessons, Next.js dashboard, and MCP tools.
★ 2 -
MCP server and Claude Code plugin for LingoChunk: gives agents your vocabulary with FSRS maturity, transcripts, native audio clips, Anki deck export and lesson saving
MIT -
Open-source forms, quizzes, lessons, courses and live games. English and Arabic, MCP, API, webhooks and self-hosting.
AGPL-3.0 ★ 1 -
Graded coding exercises inside a chat. The assistant writes the lesson and the hidden tests, the widget runs them in the browser, and a failed attempt goes back into the conversation so the tutor explains your specific mistake. Python, JavaScript, TypeScr
npm MIT -
paathshalaactive
Your AI teaches, Paathshala remembers. A free, local-first study library that Claude, Cursor or any MCP-capable AI tool fills with courses, lessons, quizzes, spaced review, Q&A and interactive 3D models. Runs on your machine, stores everything in SQLite,
npm MIT -
An AI agent that trains Earth-observation models on GEO-Bench tasks on its own and carries code-measured lessons from one dataset to the next. Strands + Claude Sonnet on Amazon Bedrock. MCP server designed to plug into GoPilot: pip install gotrain
pypi MIT -
Rigour's MCP server: lets coding agents review their change, check for an existing helper before writing a new one, and recall the team's lessons. Works with Claude Code, Cursor and other MCP clients.
npm MIT