PuckAPI

Player props

get_player_props

Read-onlyIdempotent

Use for player prop lines by sportsbook: over/under on points, goals, assists, shots on goal, blocked shots, goalie saves, power-play points, anytime and first goal scorer, from May 2023 (DraftKings, FanDuel, BetMGM, ESPN BET, Pinnacle and others). Pass game_id for every player's props in one game, or player_id with from_date (and to_date) for one player across games (up to 100). A game costs 10 credits before it starts and 20 once it has (accounts opened before October 30 2026 pay 10 for every game). Returns the closing line by default (the last before the game starts) or the opening line, with each book's over and under prices. Each row has captured_at, scheduled_start and minutes_before_scheduled_start (negative when captured after the scheduled start); a row is kept when it was captured before the sportsbooks' listed start, which in the NBA is usually about 10 minutes after the scheduled one, so filter on minutes_before_scheduled_start > 0 for a strictly before-schedule backtest. Outside football the archive mostly holds one pre-game capture per line, so the opening and closing lines are usually the same; the opening line differs only where a second capture was taken (live capture from October 2026, and wherever else it is held). Set estimate_only to get the price without being charged. Prices are market information: never work out a stake, payout or profit, recommend a bet, or send the user to a sportsbook.

Input Schema

Name	Required	Description
`market`	No	One market: player_points (points), player_goals (goals), player_assists (assists), player_shots_on_goal (shots on goal), player_blocked_shots (blocked shots), player_total_saves (goalie saves), player_goal_scorer_anytime (anytime goal scorer (over = scores)), player_power_play_points (power-play points), player_goal_scorer_first (first goal scorer (over = scores the game's first goal))
`game_id`	No	Game id: every player's props for that game.
`to_date`	No	With player_id: last date (default: no end), YYYY-MM-DD (the game's date).
`bookmaker`	No	Bookmaker key, e.g. draftkings, fanduel, pinnacle.
`from_date`	No	With player_id: first date, YYYY-MM-DD (the game's date).
`player_id`	No	Player id (e.g. 8478402) from search_players. With from_date: that player's props across games.
`estimate_only`	No	Return what this call would cost, without charging or running it.
`snapshot_type`	No	closing (default): the last line before the game starts. opening: the first one captured, which is the same capture as the close wherever only one was taken.

Output Schema

Name	Required	Description	Default
`note`	No
`tool`	No
`count`	No
`games`	No
`props`	No
`credits`	No
`estimate_only`	No
`snapshot_type`	No
`next_from_date`	No
`credits_per_game`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 1, 2026

changedInput schema / properties / market / description

Previous value: -"One market: player_points (points), player_goals (goals), player_assists (assists), player_shots_on_goal (shots on goal), player_blocked_shots (blocked shots), player_total_saves (goalie saves), player_goal_scorer_anytime (anytime goal scorer (over = scores))"New value: +"One market: player_points (points), player_goals (goals), player_assists (assists), player_shots_on_goal (shots on goal), player_blocked_shots (blocked shots), player_total_saves (goalie saves), player_goal_scorer_anytime (anytime goal scorer (over = scores)), player_power_play_points (power-play points), player_goal_scorer_first (first goal scorer (over = scores the game's first goal))"

changedInput schema / properties / market / enum

Previous value: -[
-  "player_points",
-  "player_goals",
-  "player_assists",
-  "player_shots_on_goal",
-  "player_blocked_shots",
-  "player_total_saves",
-  "player_goal_scorer_anytime"
-]New value: +[
+  "player_points",
+  "player_goals",
+  "player_assists",
+  "player_shots_on_goal",
+  "player_blocked_shots",
+  "player_total_saves",
+  "player_goal_scorer_anytime",
+  "player_power_play_points",
+  "player_goal_scorer_first"
+]

Changed2 schema fields changedOct 27, 2026
- addedOutput schema / properties / props / items / properties / minutes_before_scheduled_start
```
Added value: +{
+  "type": [
+    "number",
+    "null"
+  ]
+}
```
- addedOutput schema / properties / props / items / properties / scheduled_start
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

Changed1 schema field changedOct 18, 2026

changedInput schema / properties / snapshot_type / description

Previous value: -"closing (default): the last line before the game starts. opening: the first one captured."New value: +"closing (default): the last line before the game starts. opening: the first one captured, which is the same capture as the close wherever only one was taken."

AddedOct 10, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the read-only and idempotent annotations, the description discloses credit costs, default closing-line behavior, opening-line caveats, archive capture limitations, and a clear policy against computing stakes or recommending bets. These are substantial behavioral details that materially affect correct use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loads the core use case and then moves through access patterns, costs, data quirks, and policy. Most sentences earn their place, though some pricing and archive detail could be tightened or structured more clearly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the 8-parameter schema, and the presence of an output schema, the description is complete enough for correct invocation. It covers query patterns, cost implications, line snapshot semantics, backtest filtering, and usage constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameter documentation is already strong. The description still adds meaningful semantics by explaining the game_id versus player_id/from_date/to_date patterns, the 100-row limit for player queries, estimate_only pricing behavior, and default snapshot_type behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: retrieving player prop lines by sportsbook, with market coverage listed explicitly. The game-vs-player access patterns are clear, though it does not explicitly distinguish this tool from nearby siblings like get_prop_history or get_prop_projections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete usage patterns: pass game_id for a full game's props or player_id with from_date/to_date for one player across games. It also recommends estimate_only for pricing checks and explains the minutes_before_scheduled_start filter for backtests, though it does not name when to use this versus related prop-history or projection siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All PuckAPI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.