Skip to main content
Glama
mvtk1978

Boxerbook MCP server

by mvtk1978

Boxerbook MCP server

Boxerbook (boxerbook.com) is an open catalog of professional boxing worldwide: boxers, bouts, cards, results with sources, world titles, publisher rankings (WBC, WBA, IBF, WBO, The Ring, TBRB), the Boxerbook rating and a pre-fight forecast. The data is open under ODbL with attribution "Boxerbook".

This repository holds the public metadata of the remote MCP server and the free JSON API. The product code lives elsewhere; nothing here needs to be installed.

Connect

Endpoint

https://mcp.boxerbook.com/mcp

Transport

Streamable HTTP, stateless

Auth

none (no key, no sign-up)

Limits

300 tool calls per minute per IP; lists are capped (schedule 30 days, results 14 days, search 20)

Registry name

com.boxerbook/boxing (official MCP Registry)

JSON API

boxerbook.com/developers · OpenAPI 3.1: /v1/openapi.json

Claude Code

claude mcp add --transport http boxerbook https://mcp.boxerbook.com/mcp

Claude Desktop / claude.ai

Settings → Connectors → Add custom connector → URL https://mcp.boxerbook.com/mcp.

Cursor

.cursor/mcp.json:

{ "mcpServers": { "boxerbook": { "url": "https://mcp.boxerbook.com/mcp" } } }

ChatGPT (developer mode) and other clients

Add a remote MCP server with the URL above; no authentication.

Related MCP server: mcp-odds-api

Tools

Tool

What it answers

boxing_schedule

upcoming cards (today, tonight, weekend, 30 days) with start times, broadcasters, forecast and market consensus

boxing_results

completed bouts of the last N days with sources (days=2 is last night and today)

boxer

a boxer's card by name, slug or id: record, division, next fight, last result, rating

next_fight

a boxer's next bout with start time, broadcasters and odds

bout

one bout in full (sides' records going in, forecast, market, sources, fight-week notes)

where_to_watch

the broadcasters of a bout or card by country

rankings

the top 15 of a division: Boxerbook rating or a publisher (WBC, WBA, IBF, WBO, The Ring, TBRB)

search_boxers

boxers by name (pick by country, division and record when names collide)

search, fetch

any boxer, bout ("Inoue vs Nakatani"), card or division, and its document

Resources: boxerbook://schedule/today, boxerbook://results/last-night, boxerbook://status (data freshness), boxerbook://about. Prompts: fight_night_guide, boxer_briefing, weekend_results.

Every answer carries a url field (a boxerbook.com page) to cite. start_utc is the start of the card, not of each bout. forecast is the Boxerbook model's probability that side A wins; market is the no-vig bookmaker consensus (via The Odds API). Neither is betting advice.

Data and licence

Records are counted from open and official sources: athletic commissions (California, Nevada, Texas, Japan), sanctioning bodies, Wikidata, Wikipedia, the press. Data: ODbL, attribution "Boxerbook". This README, server.json and the examples: MIT.

Questions and corrections: info@boxerbook.com · every bout page has a "report a discrepancy" link.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to access comprehensive sports data including football, basketball, American football, and hockey leagues via 11 tools, with no API key required.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables fetching sportsbook odds, live scores, and event information across 70+ books and 30+ leagues, with tools to list sports, get scores, and discover events.
    4 npm
    1
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Real-time tennis data for ATP, WTA, Challenger and ITF: live scores, player rankings, match-winner odds, and model win-probability. 12 read-only tools; a tier-gated endpoint returns a plain-English explanation of which plan it needs rather than a bare 403. Requires a paid API key.
    24
    98 npm
    152
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    Provides AI agents with live, grounded sports data including model probabilities, track records, and European soccer and tennis arbitrage opportunities, so they answer from real numbers instead of stale guesses.
    13
    17 npm
    1
    MIT