Skip to main content
Glama
DanielTomaro13

sportsdata-mcp

entain_sgm_price

Read-onlyIdempotent

Price a custom Same Game Multi for Entain events by sending selections from one event; get the correlation-adjusted combined odds, including combinations the book hasn't pre-built.

Instructions

PRICE A SAME GAME MULTI you choose — give it selections from one Entain (Ladbrokes/Neds) event, get the correlation-adjusted combined price. Prices combinations the book has not pre-built (for those, see entain_graphql_call SportingEventPopularSameGameMultis). Several events can be priced in one call.

Returns: {prices:{:{available: true, odds:{numerator: 27, denominator: 10}}}} — keyed by event id, one entry per event you asked about. VERIFIED live 2026-08-27 against AFL Melbourne v Carlton (event eccdc4f5-e01e-4aca-afab-570869b53702), unauthenticated.

ODDS ARE FRACTIONAL AND DECIMAL = numerator/denominator + 1. 27/10 is 3.70 — not 2.7, and not 27. Confirmed against the site's own displayed prices on the same event: Melbourne showed 2.15 and returns 23/20, Over showed 1.88 and returns 22/25. Every price in entain_sport_event_card is the same shape, so the conversion is the provider's convention rather than this endpoint's quirk. FORGETTING THE +1 UNDERSTATES EVERY PRICE.

THE PRICE IS NOT THE PRODUCT OF THE LEGS. Melbourne (2.15) with Over 173.5 (1.88) prices 3.70, against a naive 4.042.

IT SILENTLY COLLAPSES A REDUNDANT LEG AND STILL SAYS available: true. Melbourne to win plus Melbourne on the line returned 23/20 — 2.15, the SINGLE-LEG price — with no echo of the legs and nothing marking the drop. Repeating one selection twice does the same. There is no leg list in the response, so RESTATE THE SELECTIONS YOU SENT whenever you report a price, and treat a price equal to a shorter combination's as a collapse.

SOME IMPOSSIBLE COMBINATIONS ARE QUOTED RATHER THAN REFUSED, AT BIG PRICES. The conflict detector is good but not complete. Every exactly-two-entrant SGM-available market on the verified event was tested (41 of them): 35 correctly refused their mutually exclusive pair, and FIVE priced it — Match Betting, both teams to win, at 146.51, plus each of the four Quarter Match Betting markets at 70-82. The failing set is the WIN-MARKET FAMILY with two entrants and an implicit draw; the three-entrant version that lists Tie as an entrant (1st Half Betting) is refused correctly.

TWO CLIENT-SIDE DEFENCES, because nothing in the payload marks exclusivity. FIRST, honour same_game_multi_available from entain_sport_event_card — THE PRICER IGNORES ITS OWN FLAG (12 of 14 markets marked unavailable were priced anyway, including the two worst impossible quotes, Highest Scoring Half at 143.65 and 1st Half Match Betting at 110.18). SECOND, do not combine two legs from the SAME market_id unless you know that market permits it: every hole found is a same-market pair. Legitimate same-market pairs do exist — nested Alternate Handicaps/Totals lines, and multi-winner props like Anytime Goal Kicker — so a blanket rule costs a little coverage and removes the whole class.

DO NOT USE num_winners FOR THIS. It was tried and it does not mean exclusivity in either direction: Melbourne Alternate Handicaps is num_winners 1 with 96 nested lines that legitimately combine, while Race To 15 is num_winners 3 with two mutually exclusive entrants.

A bet that cannot win, quoted at 146.51, looks exactly like a longshot with enormous edge, which is what an automated screener selects for. Never trust available: true as proof a combination is coherent.

WHEN IT DOES DETECT A CLASH IT IS THE BEST DIAGNOSTIC OF ANY BOOK HERE: {available: false, conflicting_selections:[{market_id, entrant_id}, …]} names the exact pair. It correctly refused Over with Under, both line sides, two margin bands, and cross-market impossibilities like Melbourne to win with Carlton by 1-39.

available: false WITH NO odds KEY is also what an unknown event returns, quietly and alongside the events that did price. Unlike the other Australian books there is no fake zero to guard against — a refusal simply has no number — but a missing odds must never be read as 0.

Malformed requests are real HTTP 400s naming the problem: a selection missing market_id or entrant_id, and event id must match key when the map key and the inner event_id disagree.

Example: Price Melbourne to win with over 173.5 points {"same_game_multies": {"eccdc4f5-e01e-4aca-afab-570869b53702": {"event_id": "eccdc4f5-e01e-4aca-afab-570869b53702", "selections": [{"market_id": "c73591e5-b00e-4c92-abfb-b3737acbdd30", "entrant_id": "49475673-c7b8-4b49-8c87-e14637ebfa5c"}, {"market_id": "2bc6b298-4fce-4545-93cd-ed232a9c69a0", "entrant_id": "8ada7d51-2a67-4bcb-9593-f9fcbbbd5188"}]}}}

Auth: works without a key; ENTAIN_REFRESH_TOKEN unlocks more if set.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
same_game_multiesYesThe whole request envelope: a MAP KEYED BY EVENT ID whose value repeats that id. {"<eventId>": {"event_id": "<eventId>", "selections": [{"market_id": "…", "entrant_id": "…"}, …]}}. THE KEY AND THE INNER `event_id` MUST BE THE SAME STRING — they are not redundant, a mismatch is a 400 saying so. Both ids per selection come from entain_sport_event_card: `market_id` is a key of `markets`, `entrant_id` a key of `entrants` (whose own `market_id` must be that market). More than one event may be priced in a single call — that is what the map is for — and each is answered independently under its own key.
Install Server

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already include readOnlyHint, openWorldHint, idempotentHint, so the risk profile is covered. The description adds a wealth of beyond-annotation behavior: fractional odds conversion (+1 gotcha), silent leg collapse, impossible combinations quoted, market_id exclusion defence, HTTP 400 on malformed requests, and the missing-odds meaning for unknown events. No contradiction exists between the description and annotations.

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 nearly every sentence carries a distinct operational fact, and the most important warnings (fractional odds, collapse, conflict detection) are front-loaded with explicit real-world confirmations. Some redundancy exists (e.g., the num_winners and same-market defences could be trimmed), but it is structured with clear paragraph breaks and an example at the end.

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?

The tool has no output schema, so the description fully describes the return shape, including the availability flag, odds key, conflicting_selections diagnostics, and missing-odds behavior. The example request and auth note complete the picture. For a pricing endpoint with these edge cases, nothing operationally necessary is left out.

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

Parameters5/5

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

Schema coverage is 100%, but the description and schema description together add critical semantic detail beyond the type: the map key must match inner event_id, the ids come from entain_sport_event_card, and the example request shows the exact nesting. The description also explains the independence of multiple event entries and the 'not just redundant' key/event_id repetition. This fully compensates and exceeds the baseline.

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?

The description leads with an explicit imperative ('PRICE A SAME GAME MULTI you choose'), specifies the resource (correlation-adjusted combined price for selections from one Entain/Ladbrokes/Neds event), and distinguishes itself from entain_graphql_call for pre-built popular SGMs. It also covers multi-event support, so an agent knows both the core action and the boundary of the tool.

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

Usage Guidelines5/5

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

The description gives strong when-to-use guidance: use for any user-selected SGM combination, and use entain_graphql_call SportingEventPopularSameGameMultis for book pre-built combinations. It also gives exclusion rules (avoid same-market pairs, don't trust the flag, don't use num_winners) and client-side defence guidance, which is more than enough for an agent to decide when to call this tool.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DanielTomaro13/sportsdata-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server