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

Odds-API MCP Server

Official
by odds-api-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Bookmaker id mappings

get_mappings
Read-onlyIdempotent

Map events and selections to a bookmaker's event, market, and outcome IDs so you can join them with odds data; query by event, market, or outcome ID, or bulk-sync upcoming and live events.

Instructions

Map our events and selections to a bookmaker's own event, market and outcome ids (for example Polymarket conditionId and token id, or Kalshi tickers), joinable to get_odds on (eventId, market, hdp, side). Look up by eventId(s), marketId(s) or outcomeId; with none of these it is a bulk sync of upcoming and live events, paged with cursor until nextCursor is null. Paid plans; the bookmaker must be in the key's selection.

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": {
      "bookmaker": "<bookmaker>"
    },
    "name": "get_mappings"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoBulk sync only: rows per page, 1-5000 (default 1000)
sportNoBulk sync only: sport slug
activeNotrue or false; both when omitted
cursorNoBulk sync only: nextCursor from the previous page
fieldsNoOptional comma-separated top-level fields to keep on each item (e.g. 'id,home,away,date,status'). Trims large responses.
leagueNoBulk sync only: league slug, requires sport
marketNoExact market name as in get_odds, case-sensitive
eventIdNoOne of our event ids
eventIdsNoUp to 10 comma-separated event ids
marketIdNoThe bookmaker's market id
bookmakerYesBookmaker name (e.g. 'Polymarket', 'Kalshi')
marketIdsNoUp to 10 comma-separated bookmaker market ids
outcomeIdNoThe bookmaker's outcome id (for Kalshi pass marketId too)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.3

TDQS

A4.7/5.0
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 behavior the annotations cannot express: the bulk-sync path is cursor-paged until nextCursor is null, access requires a paid plan, and the bookmaker must be in the key's selection. Those are exactly the operational constraints an agent needs before invoking it.

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?

Three dense sentences, front-loaded with the mapping purpose and ending with the access constraints; nothing is padding. It is slightly cramped — the semicolon-chained lookup/bulk-sync clause packs two modes into one sentence — but that costs clarity only marginally.

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

Completeness4/5

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

For a 13-parameter tool with no output schema, the description covers the essentials: both operating modes, pagination termination, plan gating, and the join key into get_odds. It does not describe the shape of returned mapping rows (e.g. which fields correspond to conditionId/token id/tickers), which is the main remaining gap given there is no output schema.

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 per-parameter meaning is already documented (limit, cursor, sport/league all say 'Bulk sync only'). The description still adds the cross-parameter semantics the schema cannot: which parameters act as lookup keys, and that omitting all of them silently switches the tool into a different bulk-sync mode — a mode switch the schema never states as a whole.

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 opens with a specific verb+resource: mapping our events and selections to a bookmaker's own event, market and outcome ids, with concrete examples (Polymarket conditionId/token id, Kalshi tickers). It also states the downstream use — joinable to get_odds on (eventId, market, hdp, side) — which cleanly separates it from siblings like get_odds, get_events and get_markets.

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?

It gives explicit mode routing: look up by eventId(s), marketId(s) or outcomeId, and with none of those supplied it becomes a bulk sync of upcoming and live events. It also names the prerequisite conditions (paid plan, bookmaker present in the key's selection) and points at get_odds as the join target, so an agent knows both when to call it and how to use the result.

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