Turn any LLM into an
intelligent tutor.
Self-learning is a superpower. Tutor MCP is an open-source Model Context Protocol server that brings 50 years of cognitive science into your favorite AI assistant.
$curl -sSL https://github.com/ArnaudGuiovanna/tutor-mcp/releases/download/v0.3.0-alpha.1/tutor-mcp_v0.3.0-alpha.1_linux_amd64.tar.gz | tar -xz
$./tutor-mcp
Anthropic
OpenAI
Mistral
Geminiget_learner_contextget_cockpit_stateWelcome back. You're on a 6-day streak and your autonomy is trending up, nice.
Heads up: goroutines have slipped to 41% retention after two days off. The spaced-repetition model is asking for a quick review before we open channels. I also noticed a tiny over-confidence bias, so we'll add a one-line prediction step before each answer.
Open Learner Model · Go
Phase · InstructionNext up → a 5-minute goroutines refresher, then we unlock channels. Ready?
Six ways people are
using their tutor.
No course catalog. No textbook. Tell your AI what you want to learn, the tutor handles sequencing, pacing, reviews, and knows when you've actually got it.
Pick up something new from scratch
« I want to learn Spanish before my trip in six weeks. »Tell your AI your goal and your deadline. The tutor maps the path, paces what comes next, and only opens new ground when the basics are solid.
Languages · coding · a new craftBring rusty knowledge back to life
« I studied statistics 8 years ago. »A short diagnostic exposes what's still solid, what's faded, and where the small wrong ideas hide. You revisit only what needs it, not a whole textbook.
Diagnostic · targeted recallPrep for an exam, interview, or certification
« AWS Solutions Architect in three weeks. »Backwards-planned from your test date. Drills focus on your weak spots; reviews peak right before D-day, when memory matters most.
Bar exam · coding interview · AWSFive focused minutes a day
« Just one thing today. »Open the chat in the morning. The tutor knows exactly which concept to revisit, delivers a single calibrated exercise, and you're done. No streaks, no homework log, no decision fatigue.
Microlearning · daily habitBuild your own bootcamp or e-learning track
« 12 weeks of data engineering, full-time, starting Monday. »Set the curriculum, the depth, and the pace. The tutor sequences modules on prerequisites, runs daily sessions, and checks mastery between phases. All the structure of a paid bootcamp or e-learning course, none of the cohort calendar.
Self-bootcamp · e-learning · self-pacedTurn any document into a course
« Turn this PDF into a six-week course. »Drop a chapter, a paper, lecture notes, and ask for the style: lecture-led, hands-on practice, Socratic dialogue, theory-first, or oral drill. The tutor maps the ideas and shapes a path that fits both the material and how you want to learn it.
PDF · pedagogical style on demandAn LLM is brilliant.
A tutor is rigorous.
Tutor MCP splits the brain in two. A deterministic cognitive engine decides whatto teach next. An LLM does what it's best at: explain, reframe, encourage. Two halves, one tutor.
Tutor MCP
50 years of cognitive science compiled into five algorithms running in parallel loops. Predictable. Auditable. No hallucinations on what you've actually mastered.
Your LLM
Trained on humanity's knowledge. Generates exercises on demand, calibrated by the engine's signals. Explains, encourages, reframes, with your full learner context in the prompt, every turn.
Tells the tutor how confident it should be that you've actually mastered a concept, not just that you happened to answer right today.
Decides when to bring a concept back, using stability and difficulty curves drawn from memory research.
Calibrates each exercise to your current ability, no more "too easy" or "too hard" guesses.
Weighs your wins and losses on each concept to predict how the next attempt is likely to go.
Ensures concepts unlock only when their prerequisites are solid. No castle on sand.
The engine decides what to teach.
Your AI teaches it ten different ways.
Determinism alone is rigid. LLMs alone drift. Together, they're the first tutor that's both rigorous and infinitely adaptable, built on the model you already trust.
Infinite content
One concept, ten exercises, never the same. No item bank to curate, no editorial team to hire.
A hundred ways to explain
Analogy, theory, story, code, real-world example. The LLM keeps reframing until it actually clicks.
Any language, any tone
Spanish travel phrases or Latin grammar. Formal exam prep or playful drilling. The tutor matches you.
Multi-modal by default
Reads your PDF, your handwritten notes, the diagram on your whiteboard, the code in your repo.
Your tutor.
Your data. Your server.
No telemetry. No SaaS lock-in. No usage caps. Self-host on a 2 GB VPS and own every byte of your learner model.
Free forever.
Always yours.
Go 1.25, SQLite, single binary. Twenty minutes to get from git clone to your first session.
From clone to first
session in ten minutes.
Self-host on your own machine or a small VPS. Connect the AI you already use. Start learning. No accounts, no waitlist, no fees.
Run the server
Clone the repo, build the single Go binary, set a JWT secret. One command later, your tutor is live on a 2 GB VPS, or your laptop.
$ go build -o tutor-mcp
$ JWT_SECRET=… ./tutor-mcp
Connect your AI
Add Tutor MCP as a custom MCP connector inside the assistant you already pay for. OAuth handles the handshake.
AnthropicOpenAIMistralGeminiTell it what you want to learn
Open your assistant, trigger the tutor, name your goal. From there, the cognitive engine takes over, pacing, gating, reviewing, encouraging.
Questions you might
have.
is a superpower.
LLMs unlocked humanity's knowledge for everyone, but knowing isn't learning. Tutor MCP brings 50 years of intelligent tutoring research back into reach, so anyone, anywhere can build durable, deep understanding from any AI conversation. Self-hosted. Open source. Free, forever.