SFX Brew

com.sfxbrewPublished by sfxbrew.comv0.1.1Updated Nov 8, 2026

Free game sound effects for AI agents: 45 Eastern and general SFX rendered locally to WAV or JS.

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

Generates procedural game sound effects locally, rendering 29 presets to WAV files or drop-in JavaScript play functions for an assistant's project.

What you can do
  • List the available sound presets and what each is suited for
  • Generate one or more WAV variants of a preset, optionally with a JavaScript file of play functions
  • Render a hand-tuned patch JSON into audio
  • Produce a single drop-in JavaScript snippet with play functions for several sounds
  • Reproduce a specific variation by seed
When to use it
Useful when building a game or interactive project that needs placeholder or final sound effects without sourcing audio files or paying per sound, especially for Eastern wuxia/xianxia style effects alongside common game sounds.
Requirements
Runs as a local process via npx, so Node.js and npm are needed. No API keys, accounts, or network access are required.
Before you install
Tools write WAV and JavaScript files to disk, so point output paths at the intended project folder. Generated sounds are stated as free for commercial use with no attribution, but verify licensing yourself before shipping.

Installation

In SourceWeft

  1. Open SFX Brew in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

sfxbrew

Procedural game sound effects for humans and AI coding agents. Eastern (wuxia / xianxia) sounds plus the usual game sounds, synthesized locally, with no API keys, no network and no per-call cost.

  • 29 presets: sword qi, guqin, pipa, erhu, wooden fish, war drum, lightning, temple bell, gong, spell cast, heavenly thunder, breakthrough, talisman, alchemy, wind chime, bamboo flute, qi gathering, coin, pickup, click, confirm, error, jump, hit, explosion, laser, power-up, level up, whoosh
  • Every generation is a fresh variation; a seed reproduces it exactly
  • Output: 16-bit WAV, or a ~7 KB dependency-free JavaScript snippet that plays the same sound with Web Audio
  • Free for commercial use, no attribution required for the sounds you generate

For AI agents (MCP)

Claude Code:

bash
claude mcp add sfxbrew -- npx -y sfxbrew mcp

Other MCP clients (Cursor, Windsurf, Claude Desktop …):

json
{  "mcpServers": {    "sfxbrew": { "command": "npx", "args": ["-y", "sfxbrew", "mcp"] }  }}

Tools:

ToolWhat it does
list_presetsPresets and what each one is good for
generate_sfxWrite one or more WAV variants (and optionally a .js file with play functions)
render_patchRender a hand-tuned patch JSON
get_js_codeOne drop-in JS snippet with playX() functions for several sounds

Then just ask: "add a coin sound and a hit sound to my game".

Agent skill

A free SKILL.md that teaches your agent when and how to use SFX Brew: skills/sfxbrew/SKILL.md, also installable from Agensi.

CLI

bash
npx sfxbrew listnpx sfxbrew coin --out assets/sfx/coin.wavnpx sfxbrew swordQi --count 5 --out assets/sfx/sword.wavnpx sfxbrew hit --seed 42 --js src/sfx.jsnpx sfxbrew render my-patch.json --out boom.wav

Sound packs

Ready-made WAV packs: Xianxia & Wuxia Game Sound Pack on itch.io (44 sounds), or download any pack as a ZIP from sfxbrew.com/sounds.

Library

js
const sfx = require('sfxbrew');const { patch, seed } = sfx.generate('coin');const { bytes } = await sfx.renderWav(patch);

Browser editor

Tweak any sound with sliders and export WAV / JS in the web editor (same engine).

License

Code: MIT. Generated sounds: yours, free for any use.

A few presets (war drum, lightning, gong, erhu) use short CC0 recordings from Freesound, listed with their recordists in samples/CREDITS.md.

Source: README.md at commit a349e56

Tools

4

list_presets

List sound presets

List the procedural sound effect presets (Eastern wuxia/xianxia sounds and general game sounds) with category, tags and what each is good for. Optionally filter by category (combat, magic, instrument, ui, items, character, ambience, creature) or a search query such as "metal", "calm" or "sword". Every call to generate_sfx with a preset gives a new random variation; pass a seed to reproduce one.

Parametersquerycategory

generate_sfx

Generate sound effect WAV files

Synthesize game sound effects locally from a preset and write 16-bit mono 44.1 kHz WAV files. Free for commercial use, no attribution. Returns file paths, the seed of each variant (reuse it to get the exact same sound) and the patch JSON (edit it and call render_patch to fine-tune). Presets: swordQi, guqin, bell, gong, spell, thunder, lightning, breakthrough, talisman, alchemy, chime, flute, qiGather, pipa, erhu, woodfish, drum, coin, pickup, click, confirm, error, jump, hit, explosion, laser, powerUp, levelUp, whoosh, arrow, swordClash, footstepStone, rain, notify, footstepGrass, land, shieldBlock, wind, campfire, stream, caveDrip, pageTurn, typing, chestOpen, monsterGrowl.

Parametersseedcountmutatepresetrequiredjs_pathout_pathrequired

render_patch

Render a custom sound patch

Render a hand-edited patch (for example one returned by generate_sfx with changed values) to a WAV file. A patch is JSON: { layers: Layer[1..6], reverb 0-1, echo 0-0.9, echoTime s, drive 0-1, crush 0|1-16 bits, gain 0-1 }. Layer fields (all optional, defaults in brackets): type: "tone"|"fm"|"string"|"pluck"|"bell"|"noise" ["tone"]; wave: "sine"|"triangle"|"square"|"sawtooth" (tone/fm/pluck) string: physically modelled plucked string (Karplus-Strong); bright 0-1 [0.5] = darker (guqin) to brighter (pipa); decay = ring time bell: partials = [[ratio, amplitude, decayMultiplier 0-1], ...] (max 16) for custom bells, gongs, wood blocks; default is a metal bar sample: a CC0 recording; sample = one of drum-center-loud, drum-center-soft, drum-edge-loud, drum-rim, lightning-1, lightning-2, gong-1, gong-2, erhu-d3, erhu-f5, sword-clash, footstep-stone, arrow, footstep-grass, land, shield-block, page-turn, typewriter, chest-open, monster-growl, campfire, stream; pitch / pitchEnd semitones (slide over slideTime); offset s into the recording; set hold ≈ recording length to let it ring naturally (lengths s: drum-center-loud 2.7, drum-center-soft 2.7, drum-edge-loud 3.5, drum-rim 1.8, lightning-1 6.5, lightning-2 7, gong-1 10, gong-2 12, erhu-d3 4.9, erhu-f5 6, sword-clash 7.2, footstep-stone 5.4, arrow 4, footstep-grass 3.2, land 2.1, shield-block 3.6, page-turn 8.75, typewriter 4.55, chest-open 11.1, monster-growl 12.8, campfire 10.4, stream 10.4) freq, freqEnd: Hz, pitch slides exponentially from freq to freqEnd; slideTime: s the slide takes (0 = whole sound) hold: s to stay at full volume before the decay starts (louder, more violent bodies) repAccel: gap multiplier per repeat (<1 speeds up, e.g. 0.86 for an accelerating drum build-up); repGain: loudness multiplier per repeat (>1 crescendo) freqPeak / cutoffPeak (Hz, 0 = off): go up to this value by the end of attack, then down to freqEnd / cutoffEnd (Doppler-like pass-by for swishes) start: s delay;

Parametersnamepatchrequiredjs_pathout_pathrequired

get_js_code

Get drop-in JavaScript for sounds

Return one self-contained JavaScript snippet (Web Audio, ~7 KB, no dependencies, no audio files) that defines play functions for several sounds. Best for browser games: paste it in and call e.g. playCoin() after a user gesture. Each sound is either {name, preset, seed} or {name, patch}.

Parameterssoundsrequired

Version history

1
  1. v0.1.1LatestNov 8, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts