Superseded listing, not a dead server. This entry was imported from an early Glama registration under com.moltlinestudio.mcp; the same server is listed under its official MCP Registry name — use com.moltlinestudio/educator. Endpoint unchanged: https://mcp.moltlinestudio.com/educator — still live, still free on the free tier. Only this duplicate entry is deprecated.
8 teaching persona and skill products plus computed classroom tools over MCP: readability_report runs a real Flesch-Kincaid analysis with leveling suggestions, grade_curve turns score lists into full distribution statistics, lesson_timer splits class periods, and get_free_skill loads any product's complete free gateway skill.
Scored across 7 tools
The three retrieval tools (get_free_skill, get_full_skill, get_full_product) form a naturally overlapping family, but each description explicitly names what it is NOT for, so an agent can pick correctly. The four utility tools (grade_curve, lesson_timer, readability_report, list_products) are cleanly distinct, with only minor residual overlap since get_full_product also returns the free skill.
All names are consistently snake_case and mostly verb_noun (get_free_skill, list_products, grade_curve). A few are noun phrases (lesson_timer, readability_report), a small deviation from the dominant verb_noun pattern but still readable and predictable.
Seven tools is well within the ideal 3-15 range for a focused toolkit. Each tool has a clear, non-redundant role: three product/skill retrieval, one catalog listing, and three free teaching utilities.
The surface covers the lifecycle for its domain: discover products (list_products), retrieve free and paid content, plus three standalone educator utilities. Minor gaps include no in-server search over the 8 products (delegated to an external catalog server) and no way to fetch persona text alone without pulling the whole product.
Load a product's free gateway skill with its complete instructions. FREE.
Typical input {"slug": "curriculum-architect-hs"} returns {"slug": ..., "skill": "", "instructions": ""}.
Returns exactly one skill - the product's free gateway skill - chosen automatically from the slug, with no plan required. Use when the caller wants usable instructions immediately. Not for the product's other skills: those are named and need get_full_skill with a skill_name, which requires a paid plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "unknown slug ''. Use list_products."}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: slug (required). Returns: object
Load one product in full: its persona plus every paid skill. PREMIUM (license).
Typical input {"slug": "curriculum-architect-hs"} returns {"slug": ..., "name": ..., "persona": "", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}.
Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: slug (required). Returns: object
Load one paid skill's complete instructions from a product. PREMIUM (license).
Typical input {"slug": "curriculum-architect-hs", "skill_name": "unit-planner"} returns {"slug": ..., "skill": ..., "instructions": ""}.
Returns one named skill, selected by skill_name. Use when the caller wants one specific paid skill. Not for the free gateway skill, which get_free_skill returns with no plan, and not for every skill at once (get_full_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: slug (required), skill_name (required). Returns: object
Summarize how an assessment landed: stats, bands, and outliers. FREE.
Reports mean, median, std dev, quartiles, distribution by percentage band, and flagged low outliers. Typical input {"scores": [88, 92, 75, 61, 84], "max_score": 100} returns {"n": 5, "mean": 80.0, "median": 84.0, "std_dev": ..., "q1": ..., "q3": ..., "distribution": {"90-100%": 1, ...}, "outliers_low": [...], "reading": "..."}.
Use on a list of scores already earned. Not for the readability of the assessment itself (readability_report). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "no scores"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: scores (required), max_score. Returns: object
Split a class period into timed segments with sensible weighting. FREE.
The opener and closer get less time; core activities get more. Typical input {"minutes": 50, "segments": ["Warm-up", "Direct instruction", "Practice", "Exit ticket"]} returns {"period_minutes": 50, "plan": [{"segment": "Warm-up", "start_min": 0, "duration_min": 8}, ...], "note": "..."}.
Use when one fixed class period must be divided into segments. Not for multi-day planning and not for spaced review, which the personal server's spaced_repetition_plan builds. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "need segments and at least 5 minutes"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: minutes (required), segments (required). Returns: object
List the 8 educator products with their included skills. FREE.
Takes no arguments. Typical input {} returns a list of 8 product objects, each {"slug": "curriculum-architect-hs", "name": ..., "tagline": ..., "skills": ["Skill A", ...], "free_skill": "Gateway Skill Name"}. Use the returned slug values with get_free_skill, get_full_product, or get_full_skill.
Returns metadata only - no persona text and no skill instructions. Use when the caller wants to see what this server covers. Not for keyword search across the whole 138-product catalog, which the catalog server's search_catalog does, and not for instructions the caller can act on (get_free_skill). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: no named parameters. Returns: result
Analyze teaching text with Flesch-Kincaid readability and leveling advice. FREE.
Typical input {"text": "", "target_grade": 6} returns {"flesch_kincaid_grade": 8.2, "reading_ease": 62.1, "sentences": N, "words": N, "avg_words_per_sentence": N, "long_sentences_over_25w": N, "polysyllabic_words_sample": [...], "target_grade": 6, "gap": 2.2, "suggestions": ["..."]}.
Use on teaching text where the reading level matters. Not for scores students earned (grade_curve) and not for general prose style, which the creator server's analyze_writing covers. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": ""} (for example {"error": "empty text"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
Inputs: text (required), target_grade. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.