Skip to main content
Glama
Sign In
getodds-mcp

getodds-mcp

Official
by getoddsapi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Public odds board for one sport (no key)

get_public_board
Read-only

Fetch DraftKings moneyline, spread, and total odds for a sport via ESPN data, including each row’s capture time—no API key required; check observed_at for freshness.

Instructions

DraftKings moneyline, spread and total prices (read through ESPN odds data) for one sport, with the capture time of every row. No API key, no credits; cached up to five minutes, so check observed_at before treating a price as current.

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": "get_public_board"
  }
}

Input Schema

NameRequiredDescriptionDefault
sportYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnly and open-world; the description adds substantial context beyond them: no authentication, no credit cost, an up-to-five-minute cache, per-row capture timestamps, and upstream provenance via ESPN. The staleness warning directly changes how an agent should interpret results, which is exactly the kind of behavior annotations cannot convey.

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?

Two dense sentences, front-loaded with the payload content, followed by cost and freshness constraints. Every clause carries information an agent needs; nothing is redundant with the title or schema.

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?

With no output schema, the description takes on the burden of describing return values and does so: three market types plus a capture timestamp per row, plus cost and cache semantics. For a one-parameter read-only lookup, nothing material is missing.

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

Parameters3/5

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

Schema description coverage is 0%, but the single parameter is a closed enum of five sport values that is self-explanatory in the schema. The description only restates 'for one sport' and adds no meaning about the enum's allowed values or behavior for unmatched sports, so it neither compensates for the gap nor has much gap to compensate for.

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?

Names the specific resource (DraftKings moneyline, spread and total prices), the scope (one sport), and the data provenance (ESPN odds feed). The explicit DraftKings book and market list let an agent distinguish this from siblings like get_fanduel_markets without opening a schema.

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

Usage Guidelines3/5

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

The 'no key, no credits' framing and the caching note imply when this tool is the cheap choice, and it gives an operational rule ('check observed_at before treating a price as current'). However, it never states when to prefer it over get_odds_board, get_odds, or the FanDuel-specific sibling, leaving that selection to inference.

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