nba-scout-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Consult a published NBA draft-scouting model (Shopping by Skill, MIT Sloan SSAC 2026) the way you'd consult a human scout: skill-by-skill tier predictions, archetypes, comparable players, the reasons behind a prediction, and an honest confidence/abstain signal. The model only ever sees pre-draft college box-score stats: no measurements, no film, no injury history. Start with search_players to resolve a name, then get_skill_profile for an overview, compare_prospects to put two players side by side, and explain_tier when you need the reasoning behind one skill's grade.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_playersA | Resolve a (possibly misspelled) player name to one or more canonical names. Use this FIRST for any player you don't have an exact, verified name for. Every other tool here accepts a canonical name and will return candidates instead of guessing if the name is ambiguous or not found. The college pipeline runs 1985-2019 and NBA outcomes 1996-2025, so very recent or very old players may not be covered; this tool tells you whether a player is in the model's training set, in the 2018 draft holdout, or neither. |
| get_skill_profileA | Full skill-by-skill scouting profile for one player: predicted tier (Bottom 25% / Middle 50% / Top 25% of all NBA players at that skill), class probabilities, confidence, the actual NBA outcome when known, and the player's archetype. Tiers are relative to the full 1996-2025 NBA population at that skill, not to the player's draft class. Defense is the model's weakest skill, so expect lower confidence there. Uses college box-score stats only. |
| compare_prospectsA | Side-by-side comparison of two players, skill by skill, with the
edge (which player, and by how much modeled probability of reaching
Top 25%) for each skill. If either player abstains on a skill (out of
distribution, or too little data), that skill is marked
not-comparable instead of picking a winner. |
| explain_tierA | Why the model predicts what it predicts: the top 5 feature
contributions (SHAP) for this player and skill, each feature's raw
value and training-set percentile, the player's archetype and distance
to its centroid, and the 3 nearest comparable players in archetype
space with their actual NBA tiers. This is the model's reasoning, not
just its answer. Use it when an agent needs to justify a scouting
claim. |
| draft_class_boardA | Rank a draft class by modeled P(Top 25%) for one skill, or by the
average across all four skills. Only the 2018 class has a genuine
holdout board right now (the model never trained on these players'
college stats). This is the tool for the "who was undervalued"
story: compare |
| find_compsB | Nearest neighbors to a player in archetype space (PCA over 12 standardized college stats), with their actual NBA outcomes when known. Good for "who does this remind you of" questions. |
| project_custom_prospectA | Score a college stat line that isn't in the database, e.g. a current prospect you found elsewhere. Provide college box-score totals/percentages using the same field names as the model (Games, Minutes_Per_Game, FG, FGA, FG%, 3P, 3PA, 3P%, FT, FTA, FT%, TRB, AST, STL, BLK, TOV, PTS, TS%, eFG%, TRB%, AST%, STL%, BLK%, TOV%, USG%, OWS, DWS, WS, WS/40, LastConf). Missing fields are treated as 0 and count toward the abstain rule, so this will usually abstain or run low confidence on a sparse stat line. That's the trust layer working as intended, not a bug. |
| get_model_cardA | The model card: data coverage, features, per-skill accuracy, and
known limitations. Also available as the |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| scouting_report | Template: call get_skill_profile, then explain_tier on the strongest and weakest skills, then write a short report that quotes the confidence and caveats. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| model_card_resource | Model card: data, features, per-skill accuracy, and known limitations. |
| archetypes_resource | The 5 player archetypes (PCA + K-means over 12 standardized college stats) with descriptions and example players. |
TDQS
Scored across 8 tools
Each tool occupies a clearly distinct slot: name resolution (search_players), single-player profile (get_skill_profile), two-player comparison (compare_prospects), reasoning/SHAP (explain_tier), archetype neighbors (find_comps), class ranking (draft_class_board), custom projection (project_custom_prospect), and metadata (get_model_card). The only conceptual overlap is that find_comps and explain_tier both surface nearest neighbors, but their framing (standalone comp search vs. per-skill justification) makes the boundary obvious, and search_players is explicitly documented as the entry point for disambiguation.
All names are snake_case and mostly follow a verb_noun pattern (find_comps, search_players, get_skill_profile, compare_prospects, explain_tier, project_custom_prospect, get_model_card). The main deviation is draft_class_board, which is noun-only and breaks the verb-first convention, plus the verb set varies (find/search/get/compare/explain/project) rather than being unified.
Eight tools is a well-scoped surface for a prospect-scouting model server, with each tool covering a distinct analytical operation rather than duplicating functionality. Nothing feels padded or missing at the count level.
The surface covers the core scouting workflow end-to-end: resolve a name, profile, compare, explain, rank a class, score an off-database prospect, and read the model card. Minor gaps remain — no way to browse/list players in the training set or pull raw college stat lines for a known player, and draft_class_board only has a genuine holdout for 2018 — but these are workable limitations rather than dead ends.