A sports betting data tool that provides bookmaker odds, events, results, markets, value-bet and arbitrage information, and related line data. Odds are prices offered by bookmakers on possible outcomes.

Use it to look up events and live games, compare odds, inspect historical results, study changing or closing lines, or check bet settlement information.

It avoids relying on guessed sport, league, market, or bookmaker names and provides a defined process for finding the relevant data.

odds-api — Skill for Claude Code and Codex by odds-api-io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add odds-api-io/odds-api-mcp-server --skill odds-api

Clone the repo

git clone --depth 1 https://github.com/odds-api-io/odds-api-mcp-server

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/odds-api-io/odds-api-mcp-server/odds-api/github.svg)](https://agentmods.dev/skills/odds-api-io/odds-api-mcp-server/odds-api)

Your own site

<a href="https://agentmods.dev/skills/odds-api-io/odds-api-mcp-server/odds-api"><img src="https://agentmods.dev/badge/skills/odds-api-io/odds-api-mcp-server/odds-api/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/odds-api-io/odds-api-mcp-server/odds-api"><img src="https://agentmods.dev/badge/skills/odds-api-io/odds-api-mcp-server/odds-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.01101
Opus 5.5	$0.00024	$0.00440
Sonnet 5.5	$0.00012	$0.00220
Haiku 4.5	$0.00006	$0.00110

Measured 4d ago against content hash a989878e819f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odds-api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/odds-api/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Odds-API.io agent guide

The odds-api MCP server wraps the Odds-API.io v3 REST API: odds from 450+ bookmakers across 34 sports. The API key comes from the ODDS_API_KEY environment variable only; never ask the user to paste it into the chat and never repeat it.

Call order

Slugs first. get_sports gives sport slugs, get_leagues gives league slugs. Never guess a slug.
Find the event. search_events (team name, status=live for in-play), get_events (sport + league + date window) or get_live_events. Past matches: search_historical_events or get_historical_events.
Market names. get_markets lists the exact names per sport. Use ML, Spread, Totals; there is no "Match Winner", "Over/Under" or "Asian Handicap".
Bookmakers. Odds tools only return bookmakers in the key's selection: check get_selected_bookmakers. get_bookmakers shows each book's status (ok, degraded, down) when one is missing.
Prices. get_odds or get_multi_odds (up to 10 events, one request) with bookmakers and markets. For "best price" or "fair price" questions use get_odds_summary.

Keep responses small

Always pass markets to get_odds, get_multi_odds and get_historical_odds.
List tools accept fields (keep only some keys per item) and maxResults; get_events also takes limit/skip.
get_outright_odds takes markets and maxRunners: a full golf field is 150+ runners per market.
Pass sport to get_dropping_odds; without it player props dominate.

Which tool for which job

Job	Tool
Best / average / fair price	`get_odds_summary` (Growth plan and above; lower plans get `demo: true` sample data, say so)
Line history for one book	`get_odds_movements` (prematch; a 404 lists what does exist)
Value bets / arbitrage / steam	`get_value_bets`, `get_arbitrage_bets`, `get_dropping_odds`
Closing line value, backtests	`get_closing_lines` (up to 10 leagues, 366 days, 100 events per page)
Did my bet win?	`get_settlements`, `grade_bets` (up to 50 at once)
Golf outrights	`list_outrights` then `get_outright_odds` / `get_outright_results` (Outrights add-on)
Polymarket / Kalshi ids	`get_mappings`
Requests left this hour	`get_usage`

Read the full file on GitHub · 55 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 55 lines · 61 tokens per session scan A a989878e819f

Subscribe to this mod's changes

odds-api is a skill published in the GitHub repository odds-api-io/odds-api-mcp-server (2 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 1,101 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Finance and fintech betting-odds claude mcp mcp-server model-context-protocol odds-api

odds-api next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
odds-apiodds-api-io/odds-api-mcp-server	Skill	2	5d ago	MIT	A	61	Claude Code, Codex
haystack-router-interactionGoPlausible/algorand-mcp	Skill	44	yesterday	MIT	A	65	Claude Code, Codex
blazemeter-usage-billingBlazemeter/bzm-mcp	Skill	26	16d ago	Apache-2.0	A	67	Claude Code, Codex
award-travelAwardTravelFinder/mcp	Skill	12	11d ago	MIT	A	164	Claude Code
find-my-bookings-and-balancesAwardTravelFinder/mcp	Skill	12	11d ago	MIT	A	97	Claude Code
where-can-my-points-take-meAwardTravelFinder/mcp	Skill	12	11d ago	MIT	A	75	Claude Code
cancel-or-change-awardAwardTravelFinder/mcp	Skill	12	11d ago	MIT	A	69	Claude Code