Skip to main content
Glama
Sign In
Odds-API MCP Server

Odds-API MCP Server

Official
by odds-api-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

List outright tournaments

list_outrights
Read-onlyIdempotent

Lists outright (futures) tournaments for a sport, sorted by date, returning IDs and pricing status so you can fetch odds next.

Instructions

List outright (futures) tournaments for a sport, sorted by date: id, name, date, status, league and bookmakerCount (0 = not priced yet). Golf only today: PGA Tour, DP World Tour, LIV Golf and the majors. Call this first, then get_outright_odds with the id. Needs the Outrights add-on: a 403 means the key does not have it, so tell the user the message (it links to where to add it) and do not retry.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sport": "<sport>"
    },
    "name": "list_outrights"
  }
}

Input Schema

NameRequiredDescriptionDefault
sportYesSport slug. Currently 'golf'
fieldsNoOptional comma-separated top-level fields to keep on each item (e.g. 'id,home,away,date,status'). Trims large responses.
leagueNoLeague slug: pga-tour, dp-world-tour, liv-golf or majors
statusNoComma-separated: pending, live, settled, cancelled. Default pending,live
maxResultsNoOptional cap on the number of items returned to you (applied after the API call).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.3

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds behavior they cannot convey: results are date-sorted, the meaning of bookmakerCount=0, the current sport coverage, and an add-on entitlement prerequisite with a prescribed 403 response (surface the message, do not retry). That is exactly the extra context the annotations cannot supply.

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

Conciseness5/5

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

Front-loaded with purpose and return shape, then sequencing, then the failure path. Every clause carries information (field list, sort order, bookmakerCount semantics, add-on requirement); nothing is filler despite the density.

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?

No output schema exists, but the description names the returned fields and the meaning of the ambiguous one, and it covers the authorization failure mode. Nothing an agent needs in order to call this correctly and handle the response is missing.

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 the baseline is 3; the description exceeds it by restricting the sport to golf and effectively enumerating the valid league slugs (PGA Tour, DP World Tour, LIV Golf, majors), which the schema lists without stating that golf is the only working value today.

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 ('List outright (futures) tournaments for a sport'), adds ordering ('sorted by date') and enumerates the returned fields, then explicitly distinguishes itself from the sibling that consumes its output ('then get_outright_odds with the id').

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?

Gives explicit sequencing ('Call this first, then get_outright_odds with the id'), an explicit scope limit ('Golf only today'), and explicit failure handling ('a 403 means the key does not have it... do not retry'). The agent knows when to use it and what to do when it fails.

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

Deploy Server

Other Tools