FighterAPI MCP server
Provides access to UFC fight data, including results, judges' scorecards, round-by-round stat sheets, fighter profiles, career rates, Elo ratings, and sportsbook moneylines.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
FighterAPI MCP server
The fight data API. Results, judges' scorecards and the full stat sheet for nearly every UFC fight since 2000, round by round, plus PFL (2012 on) and Bellator (2009 to 2024) results, fighters and ratings with the same key. Fighter profiles, career rates, our own ratings and sportsbook moneylines (UFC from June 2020, PFL from April 2023, Bellator from January 2022 to 2024). REST API and MCP server. 500 free credits every month, no card.
Website: https://fighterapi.com · Docs: https://fighterapi.com/docs · Get a key: https://fighterapi.com/signup
You: "What is Islam Makhachev's significant strike accuracy by round across his UFC fights?"
Claude: [calls get_fighter_fights]
You: "Show the opening and closing moneyline for every main event this year."
Claude: [calls get_odds]Run it locally (stdio)
Most clients connect to https://mcp.fighterapi.com/mcp directly. For a client that launches a local process instead:
git clone https://github.com/noahowsh/fighterapi-mcp.git && cd fighterapi-mcp && npm install
FIGHTERAPI_API_KEY=your_key node index.js{ "mcpServers": { "fighterapi": { "command": "node", "args": ["/path/to/fighterapi-mcp/index.js"], "env": { "FIGHTERAPI_API_KEY": "your_key" } } } }It forwards to the hosted server with your key, so every tool and credit cost is the same.
Related MCP server: jktjj-mcp
Skills
Sixteen Claude skills that turn Claude into an MMA analyst wired to these tools: fight and card lookup, fighter scouting, per-round striking and grappling rates, Elo by weight class, odds comparison and devigging, favourite calibration, edge detection and backtesting. They are plain SKILL.md files in skills/.
git clone https://github.com/noahowsh/fighterapi-mcpOr install them as a Claude Code plugin:
/plugin marketplace add noahowsh/fighterapi-mcp
/plugin install fighterapi-skills@fighterapiOr with the skills CLI: npx skills add noahowsh/fighterapi-mcp.
Point Claude at the skills/ folder (for Claude Code, copy or symlink the skill folders into ~/.claude/skills/ or a project's .claude/skills/), connect the MCP server below, and ask. Start with skills/dispatch if you are unsure which skill fits. Full catalog: skills/README.md.
Useful pages
Docs and every tool: https://fighterapi.com/docs
Guides: https://fighterapi.com/guides
UFC odds: https://fighterapi.com/odds
Data coverage: https://fighterapi.com/data
Pricing: https://fighterapi.com/pricing
Compare: ESPN MMA API, Kaggle UFC dataset, Sportradar and SportsDataIO, UFC Stats scraper
Python
The official Python client is on PyPI: fighterapi.
pip install fighterapi
export FIGHTERAPI_API_KEY=sk_live_...from fighterapi import Client
client = Client()
events = client.list_events(status="final", limit=3)["events"]
for e in events:
print(e["event_id"], e["event_date"], e["name"])Typed errors for a bad key, no credits left, not found and rate limits, automatic retries, and to_dataframe for pandas.
Quick start
This is a hosted (remote) MCP server over Streamable HTTP. There is nothing to install.
Claude Code
claude mcp add --transport http fighterapi "https://mcp.fighterapi.com/mcp?key=YOUR_API_KEY"Claude Desktop, Cursor and other clients
{
"mcpServers": {
"fighterapi": {
"url": "https://mcp.fighterapi.com/mcp?key=YOUR_API_KEY"
}
}
}The key can also be sent as an x-api-key header or Authorization: Bearer. Connecting and listing tools works without a key; calling a tool needs one.
REST
curl -X POST https://mcp.fighterapi.com/v1/list_events -H "x-api-key: YOUR_API_KEY"Every tool is POST /v1/{tool} with a JSON body.
Examples
Runnable Python (standard library only) and Node 18+ (no dependencies) examples live in examples/:
examples/python/quickstart.pyandexamples/node/quickstart.mjs: schedule plus a headline call.examples/python/mma_fighter_record_and_odds.py: A fighter profile (UFC record by method, Elo, career strike and takedown rates), their recent fights with the median closing line, and every sportsbook's open and close moneyline for their latest fight.
export FIGHTERAPI_API_KEY=your_key
python3 examples/python/quickstart.py
node examples/node/quickstart.mjsSee examples/README.md for details. Get a free key (500 credits a month, no card) at https://fighterapi.com/signup.
Tools (11)
Tool | What it returns |
| Cards by year and status, with the main event |
| Find fighters by name or nickname |
| A card's fights with results, method, round, time and judges' scores |
| Upcoming fights with current moneylines where a book has posted one |
| Our fighter ratings (Elo from every UFC result since 2000) |
| One fight: result, full stat sheets, round-by-round lines, ratings and odds |
| Profile, UFC record by method, career rates, rating and recent fights |
| A fighter's full UFC history with stats, ratings and closing lines |
| Career leaderboards from every fight's stat sheet |
| Opening, closing and current moneylines by sportsbook for a fight (5) or a card (10) |
| Snapshots of each posted line before a fight |
Leagues: mma (default, UFC), pfl, bellator (pass league to any tool).
Data
Every UFC card since 2000 with results, method, round, time and judges' scorecards; the full stat sheet, round by round, for nearly every card
PFL (2012 on) and Bellator (2009 to 2024) results, fighters and ratings; no stat sheets exist for those promotions in recent years
Fighter profiles with reach, stance and gym, career rates by method, and our Elo ratings from every UFC result since 2000
Moneylines and total rounds, no props: UFC opening and closing lines from June 2020 (a median of 5 to 7 books per fight; usually one book since mid-2024), PFL from April 2023 and Bellator from January 2022 to 2024 with fewer books; pre-fight snapshots: once a day from October 2026, and every hour in the two days before a fight
Coverage by season, read live from the database: https://fighterapi.com/docs
Pricing
500 free credits every month, no card. Plans: Starter $19/mo (10,000 credits), Pro $49/mo (30,000), Scale $149/mo (125,000). Wallet top-ups from $5, never expire. https://fighterapi.com/pricing
Attribution
Ratings are ours. Not affiliated with the UFC, PFL, Bellator or any promotion.
License
MIT for the contents of this repository. Data terms as above.
Use with Codex
Add this repo as a Codex plugin marketplace, then install the plugin:
codex plugin marketplace add noahowsh/fighterapi-mcpThen open the plugin directory in Codex and install fighterapi-skills from the fighterapi marketplace. The plugin bundles the skills in skills/ and the FighterAPI MCP server (https://mcp.fighterapi.com/mcp). Set your key first (free at https://fighterapi.com/signup):
export FIGHTERAPI_API_KEY=your_keyCodex sends it as a bearer token.
Use with Gemini CLI
export FIGHTERAPI_API_KEY=your_key
gemini extensions install https://github.com/noahowsh/fighterapi-mcpThe extension adds the FighterAPI MCP server (https://mcp.fighterapi.com/mcp) and sends the key in the x-api-key header. Get a free key (500 credits a month) at https://fighterapi.com/signup.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Independent statistical feature evaluation for machine learning and forecasting. ML Referee tests up to 1,000 candidate features in one run against a declared baseline, helping researchers and AI agents decide which inputs to pursue, which bounded feature repairs merit further testing, and where more evidence is needed—without a separate ablation run for every feature. Use the MCP tools to discover input schemas, check access and credits, preflight a dataset, obtain a quote, submit an authorized evaluation, and retrieve structured results and reports. Results are scoped to the submitted evidence and evaluation design; they do not guarantee future model performance. Invite-only beta with manual approval. Public tool discovery requires no authentication; account and evaluation tools require OAuth through approved client connections and available evaluation credits. Connect directly to https://api.mlreferee.com/mcp. Website: https://mlreferee.com Request beta access: https://mlreferee.com/beta Agent setup and documentation: https://mlreferee.com/agents
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Hosted MCP server for live public-data APIs and Skills for AI agents.
Read-only search of 2,189 AI agent tools (MCP servers, x402 APIs) with daily automated trust scores.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks.2929 npm20 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AI agent access to JKTJJ's structured BJJ data — gyms, coaches, events, and cities worldwide.1MIT
- AlicenseAqualityCmaintenanceMCP server for the FootballStack football data API. Gives LLM clients and AI agents (Claude, Cursor) access to real football data — fixtures, standings, lineups, live events, shot-level xG with pitch coordinates, and model-derived fair odds.12MIT
- AlicenseNot gradedqualityBmaintenanceEnables an agent to query MMA data—fight schedules, results, per-round stats, rankings history, judges' scorecards, and consensus odds—across UFC and other promotions directly via Model Context Protocol.120 npmMIT