Skip to main content
Glama
FastballAPI MCP Server

FastballAPI MCP Server

FastballAPI MCP server

Smithery MCP Registry

The baseball data API. Pitch-by-pitch data with pitch type, velocity and location, every plate appearance with base-out state and the batted ball, box scores, standings, our own ratings and run values, sportsbook lines by book and MLB player prop lines. MLB since 2015 plus the NCAA Division I games we cover. REST API and MCP server. 500 free credits every month, no card.

Website: https://fastballapi.com · Docs: https://fastballapi.com/docs · Get a key: https://fastballapi.com/signup

You:    "What is Gerrit Cole's whiff rate by pitch type this season?"
Claude: [calls get_pitch_mix]

You:    "How often did Aaron Judge homer on a 3-2 count in 2025?"
Claude: [calls get_plate_appearances]

You:    "How often has Shohei Ohtani gone over his total bases line since 2023?"
Claude: [calls get_prop_history]

Run it locally (stdio)

Most clients connect to https://mcp.fastballapi.com/mcp directly. For a client that launches a local process instead:

git clone https://github.com/noahowsh/fastballapi-mcp.git && cd fastballapi-mcp && npm install
FASTBALLAPI_API_KEY=your_key node index.js
{ "mcpServers": { "fastballapi": { "command": "node", "args": ["/path/to/fastballapi-mcp/index.js"], "env": { "FASTBALLAPI_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: Statcast MCP Server

Skills

This repo also ships 16 free Claude skills in skills/ that turn Claude into a baseball analyst: pitch mix and whiff rate, run value, spray charts, Pythagorean record, game previews, odds analysis, prop modeling (pitcher strikeouts, hits, total bases), edge detection and backtesting. Each skill names the FastballAPI tools it calls and what they cost.

git clone https://github.com/noahowsh/fastballapi-mcp.git

Or install them as a Claude Code plugin:

/plugin marketplace add noahowsh/fastballapi-mcp
/plugin install fastballapi-skills@fastballapi

Or with the skills CLI: npx skills add noahowsh/fastballapi-mcp.

Point Claude at the skills/ folder, connect the MCP server below, and ask. The dispatch skill routes a request to the right two or three skills. Full list: skills/README.md.

Python

The official Python client is on PyPI: fastballapi.

pip install fastballapi
export FASTBALLAPI_API_KEY=sk_live_...
from fastballapi import Client, to_dataframe

client = Client()

props = client.get_player_props(
    game_id="401815991",
    market="batter_home_runs",
)
df = to_dataframe(props, key="props")
print(df[["player_name", "bookmaker", "line", "over_odds", "under_odds"]].head(10))

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 fastballapi "https://mcp.fastballapi.com/mcp?key=YOUR_API_KEY"

Claude Desktop, Cursor and other clients

{
  "mcpServers": {
    "fastballapi": {
      "url": "https://mcp.fastballapi.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.fastballapi.com/v1/list_teams -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/:

export FASTBALLAPI_API_KEY=your_key
python3 examples/python/quickstart.py
node examples/node/quickstart.mjs

See examples/README.md for details. Get a free key (500 credits a month, no card) at https://fastballapi.com/signup.

Tools (20)

Tool

What it returns

list_teams

Team ids, abbreviations and colours for a season

search_players

Find players by name

get_games

Games with runs, hits and errors by season, date, range or team

get_schedule

Upcoming games with the median line across sportsbooks

get_standings

Standings from every final game, with run differential and Pythagorean record

get_injuries

The latest injury report

get_ratings

Our team Elo ratings, ranked

get_game

One game: every batting and pitching line, each book's line, win probability

get_player

Season batting (AVG, OBP, SLG, OPS, RE24) and pitching (ERA, WHIP, K/9)

get_player_games

A player's full batting and pitching game log

get_leaders

Season leaders among qualified batters and pitchers

get_team_stats

Runs for and against, team batting and opponents' batting

get_pitch_mix

A pitcher's arsenal: usage, velocity, whiff rate per pitch type

get_odds

Every sportsbook's moneyline, run line and total for a game (5) or a day (10)

get_plate_appearances

Plate-appearance play-by-play with base-out state, batted ball, win probability, RE24

get_pitches

Pitch-by-pitch: count, type, velocity, location, result

get_spray_chart

Where a batter or team hits the ball, by trajectory and field

get_line_movement

Snapshots of each sportsbook's line before first pitch

get_player_props

Player prop lines by sportsbook, opening and closing

get_prop_history

A player's prop lines against the result, game by game

Leagues: mlb (default), ncaabase (NCAA Division I games we cover; pitch tools, spray charts and injuries are not offered for college).

Data

  • MLB games since 2015 with pitch-by-pitch data (every pitch from 2018; 2015 to 2017 have about 98 to 99% of each season's pitches)

  • Every plate appearance with base-out state, batted ball, win probability and RE24

  • Per-sportsbook moneylines, run lines and totals: 4 to 13 books per game from 2015 to 2023 (about 4 in 2015, 10 in 2016 and 2017, 7 to 8 in 2018 to 2020, 12 in 2021 to 2023), usually one book since 2024, plus opening and closing lines since July 2020 (a median of 7 books in 2021 to 2023 and 8 since 2024); pre-game line snapshots from launch: once a day, and every hour for games in the next two days

  • MLB player prop lines by sportsbook (hits, home runs, total bases, RBI, pitcher strikeouts, pitcher outs) from May 2023, with the result against each line (get_player_props, get_prop_history); none for college

  • NCAA Division I college baseball for the games we cover (not every Division I game)

Coverage by season, read live from the database: https://fastballapi.com/docs

Useful pages

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://fastballapi.com/pricing

Attribution

Ratings and run values are ours. Not affiliated with MLB, the NCAA or any team.

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/fastballapi-mcp

Then open the plugin directory in Codex and install fastballapi-skills from the fastballapi marketplace. The plugin bundles the skills in skills/ and the FastballAPI MCP server (https://mcp.fastballapi.com/mcp). Set your key first (free at https://fastballapi.com/signup):

export FASTBALLAPI_API_KEY=your_key

Codex sends it as a bearer token.

Use with Gemini CLI

export FASTBALLAPI_API_KEY=your_key
gemini extensions install https://github.com/noahowsh/fastballapi-mcp

The extension adds the FastballAPI MCP server (https://mcp.fastballapi.com/mcp) and sends the key in the x-api-key header. Get a free key (500 credits a month) at https://fastballapi.com/signup.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides access to comprehensive MLB baseball statistics through the MLB Stats API, pybaseball library, Statcast data, FanGraphs, and Baseball Reference, including support for generating matplotlib visualizations.
      34
      -
    • A
      license
      A
      quality
      D
      maintenance
      Enables users to query MLB Statcast, FanGraphs, and Baseball Reference data using natural language through an AI assistant. It provides comprehensive tools for analyzing player performance, pitch-level data, season leaderboards, and team standings.
      24
      36
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides comprehensive baseball analytics through 32 tools covering pitching, batting, defensive metrics, and visualizations via the Model Context Protocol, enabling natural language queries for advanced Statcast and MLB statistics.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides access to official MLB statistics via a keyless API, enabling AI agents to query MLB data through natural language or direct tools.
      292 npm
      MIT