webdata-tools-mcp

Get sports scores, box scores, odds and standings

get_sports_data

Read-onlyIdempotent

Fetch sports scores, schedules, player box scores, betting odds, standings and rosters across 24 leagues, filtered by date, status, team or player.

Instructions

Scores and schedules, player box scores, betting odds (opening vs current or closing moneyline, spread and total, line movement, no-vig probability, and how each line settled), standings and rosters for 24 leagues: NFL, NBA, WNBA, MLB, NHL, college football and basketball, Premier League, LaLiga, Bundesliga, Serie A, Ligue 1, Champions League and more, MLS, Liga MX, Formula 1, ATP and WTA tennis (with rankings), PGA golf and UFC. Filter by date, status and team or player. Runs the Apify Actor tacps126/sports-data on your Apify account (about $0.003 per game, odds row, standings row or player; $0.001 per box-score player line; spend per call is capped at $0.5).

Input Schema

Name	Required	Description	Default
`teams`	No	Team or player names or abbreviations, e.g. ["Lakers", "KC", "Sinner"].
`season`	No	Season year for standings, e.g. 2026; empty = current.
`date_to`	No	YYYY-MM-DD; replaces days_ahead.
`leagues`	Yes	One or more leagues.
`data_type`	No	games, boxScores (one row per player per game), odds (one row per game per sportsbook), standings (tennis: rankings), teams or rosters. Box scores, teams and rosters cover team sports.	games
`date_from`	No	YYYY-MM-DD; replaces days_back.
`days_back`	No	Days back from today; 1 = yesterday and today.
`max_items`	No	Maximum results to return (default 100, max 5000). Cost scales with this.
`days_ahead`	No	Days ahead for schedules and upcoming lines.
`match_type`	No	Tennis only.	any
`extra_input`	No	Advanced: extra Actor input fields, merged over the defaults.
`game_status`	No	final for results and closing lines, scheduled for fixtures.	any

Output Schema

Name	Required	Description
`tool`	Yes	Name of the tool that produced the result.
`count`	Yes	Number of records the Actor returned.
`items`	Yes	The records. Long text fields are shortened to 600 characters.
`shown`	Yes	Number of records included in `items` (can be lower than count when the result is long).
`truncated`	Yes	True when records were left out to keep the result short; ask for fewer items.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.14.0Nov 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds the material behavior an agent cannot get from them: it runs a specific Apify Actor on the user's own account, itemized per-unit pricing, and a hard $0.5 per-call spend cap. That cost and account-execution disclosure is exactly the kind of context annotations omit.

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?

Front-loads the data types, then the league list, then the filter knobs, then the pricing/cap caveat — a sensible order with no filler sentences. The long league enumeration and odds-detail parenthetical are dense but each clause carries distinct information, so it stays close to appropriately sized for a 12-parameter, 24-league tool.

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?

An output schema exists, so return-shape explanation isn't needed. The description covers domain scope, filtering, per-unit cost, spend ceiling, and the external Actor dependency — everything an agent needs to decide to call it and to call it correctly.

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 coverage is 100%, so baseline is 3, but the description adds meaning the schema doesn't: what an 'odds' row contains (opening vs current/closing moneyline, spread, total, line movement, no-vig probability, settlement) and that tennis rankings come back under 'standings'. It also flags that cost scales with max_items, tying a spend consequence to a parameter.

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

Purpose5/5

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

States a specific verb and resource set: scores and schedules, box scores, betting odds, standings and rosters, enumerating the 24 leagues covered. No sibling tool in the list touches sports, so an agent can immediately route sports queries here.

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?

"Filter by date, status and team or player" plus the data_type breakdown gives clear context on how to scope a call, and the schema's data_type description notes box scores/teams/rosters are team-sports-only. There are no explicit when-not-to-use conditions, but no sibling overlaps this domain, so the exclusion burden is low.

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