Schedule spaced reviews and exam study plans from each learner's forgetting curve.
Scored across 2 tools
The two tools are mostly distinct: learning_optimizer is the normal analysis path up to 2,000 rows, while learning_get_engine is explicitly for larger logs or sandbox-resident files. There is still some conceptual overlap because both run the same engine and produce similar outputs, so an agent must rely on the size/location boundary stated in the descriptions.
Both names share the learning_ prefix, which helps grouping. However, learning_optimizer is a noun phrase while learning_get_engine follows a prefix_verb_noun pattern, so the naming convention is mixed rather than fully predictable.
Two tools is thin for a general MCP server, but the split is purposeful: one main analysis tool and one escape hatch for oversized or sandboxed inputs. It is borderline but reasonable for a narrow, stateless optimization service.
The surface covers the core learning-optimization workflow, including review prioritization, retention forecasts, exam planning, and large-log handling via the engine script. Minor gaps may exist around explicit data validation or multi-run persistence, but the main operational paths appear covered.
For review logs over 2,000 rows, or any review file already in your code sandbox. Returns a complete numpy-only Python script with the same engine as learning_optimizer; it reads the file(s), prints the decision cards and writes every learner's lists, exam plans and item states to learning_result.json. Pass other inputs (exam_date, daily_review_limit, target_retention ...) in params. No learner data reaches this server on this path.
Inputs: params, items_path, reviews_path. Returns: notes, script, language, requires, +8 more
Rebuilds each learner's memory of each item from a review log (who answered what, when, how well) and returns: today's review list per learner, most-at-risk first; chance of remembering each item now, in 7 and 30 days; the next review date for a retention target; a day-by-day plan to an exam date within a daily limit, with the daily effort needed if the limit is too low; items that keep slipping; questions most learners miss; neglected topics; and how much daily work 85/90/95% retention costs. Memory models: FSRS-6 (matches py-fsrs 6.3.2 exactly), a per-learner personalised version, half-life regression and SM-2 — the schedule is chosen by measured accuracy on the most recent answers. Output starts with plain decision cards (REVIEW TODAY, CATCH UP, STUDY MORE, ON TRACK FOR EXAM, SHORTER GAPS, TRY ANOTHER WAY, REWRITE ITEM, REVISE TOPIC, PROTECT PRIVACY ...). Up to 2,000 review rows; larger logs: learning_get_engine.
Inputs: reviews (required), as_of, items, learners, +16 more. Returns: alerts, status, content, message, +7 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Map prerequisites, track mastery and recommend the next topic each learner is ready for.
Save the courses you make with AI and review them with spaced repetition and a daily session.
Flashcards, multiple-choice quizzes, mind maps and spaced-repetition reviews from your study notes.
Agent-native spaced-recall system of record. Deterministic dueAt via remote MCP for Muse/any agent.
Add one secure layer between your agents and this server.
