webear and web perception

"The beat sounds muddy"→ your AI captures 3 seconds, measures the spectral centroid at 580 Hz with 45% energy below 250 Hz, and tells you exactly why.

Browser (Web Audio API) ↓ MediaRecorder taps the AudioContext output node ↓ Uploads WebM blob via HTTP POST Express Middleware (your dev server) ↓ Stores captures in memory, dispatches commands via SSE MCP Server (stdio — runs inside your IDE) ↓ Retrieves captures, sends to CodedSwitch analysis API AI Coding Assistant → "Your bass band is 42% of the mix (high), spectral centroid is 580 Hz (muddy), and timing jitter is 23ms — the scheduler is drifting under load."

The key difference from every other audio MCP:this taps the Web Audio graph directly, bypassing room acoustics, microphone hardware, and the need to export files.

2. Add the Express middleware to your dev server

import express from 'express' import { webearMiddleware } from 'webear/middleware' const app = express() app.use(express.json()) // Mount the audio debug bridge (automatically disabled in production) app.use('/api/webear', webearMiddleware()) app.listen(5000)

3. Add the client snippet to your web app

Option A — auto-detect everything (Tone.js or raw Web Audio)

import WebEar from 'webear/client' WebEar.init()

const ctx = new AudioContext() const masterGain = ctx.createGain() masterGain.connect(ctx.destination) WebEar.init({ audioContext: ctx, outputNode: masterGain })

import  as Tone from 'tone' WebEar.init({ toneJs: true })

import  as THREE from 'three' const listener = new THREE.AudioListener() camera.add(listener) WebEar.init({ tapNode: listener.getInput() })

<script src="node_modules/webear/client-snippet.js"></script> <script>WebEar.init()</script>

Claude Code(.mcp.jsonin project root):

Free tier: 50 analyses/day. No credit card required.

6. Start your dev server, open your app, play audio, then ask your AI:

"Capture 3 seconds and tell me why the bass sounds muddy."

"Compare the audio before and after my last commit."

"Is there any clipping in the high-frequency range?"

── Audio Analysis Report ────────────────────────────── Duration: 3.02s ── Loudness ───────────────────────────────────────── RMS: -12.4 dBFS Peak: -1.2 dBFS Dynamic range: 11.2 dB Crest factor: 3.63 Clipping: none ── Tone ────────────────────────────────────────────── Spectral centroid: 2847 Hz DC offset: 0.00012 (ok) ── Frequency Bands ─────────────────────────────────── Sub (20-80 Hz): 8.2% Bass (80-250 Hz): 22.1% Mid (250-2k Hz): 38.4% Hi-mid (2-6k Hz): 21.8% High (6k+ Hz): 9.5% ── Rhythm ──────────────────────────────────────────── Estimated BPM: 92 Onset count: 12 Timing jitter: 4.2 ms std dev ── Summary ─────────────────────────────────────────── Loudness: -12.4 dBFS RMS, peak -1.2 dBFS. Tone: balanced (centroid 2847 Hz). Band mix — sub: 8% | bass: 22% | mid: 38% | hi-mid: 22% | high: 10%. Rhythm: estimated 92 BPM, 12 onsets detected. Timing: very tight (< 5 ms jitter).

── Audio Diff: a1b2c3d4… → e5f6g7h8… ── ── Loudness ────────────────────────────────────────── RMS: -14.2 dBFS → -12.4 dBFS (+1.8 dBFS) ⚠ Peak: -3.1 dBFS → -0.2 dBFS (+2.9 dBFS) ⚠ CLIPPING INTRODUCED — gain staging regression ── Tone ────────────────────────────────────────────── ⚠ Spectral centroid: 2847.0 Hz → 1920.0 Hz (-927.0 Hz) ── Interpretation ──────────────────────────────────── A gain bug was introduced that causes clipping. Tonal character changed noticeably — EQ or filter behaviour may have shifted.

webearMiddleware({ maxCaptures: 50, // Max captures in memory (default: 50) maxAgeMins: 10, // Auto-evict after N minutes (default: 10) maxUploadBytes: 50e6, // Max upload size (default: 50MB) devOnly: true, // Disable in production (default: true) })

WebEar.init({ audioContext: myCtx, // Your AudioContext instance outputNode: myGainNode, // The node to tap (defaults to destination) toneJs: true, // Auto-detect Tone.js context bridgeBase: '/api/webear', // Override API path devOnly: true, // Only init outside of production (default: true) })

- Web Audio / Tone.js developers— debug beats, synths, effects, and mixing without leaving your IDE
- Game audio developers— verify sound effects, spatial audio, and mixing in real-time
- Music app builders— catch regressions between code changes withdiff_audio
- Podcast / streaming apps— validate audio quality, levels, and encoding
- Anyone whose app makes sound— if it has a Web Audio graph, your AI can now hear it

Microphone MCPs capture room sound — your fan noise, chair creaks, and room reverb are all in the recording.webeartaps the Web Audio APIbefore it hits the DAC, giving you a clean digital signal with no room artifacts.

WebEar started as audio-only.Web Perceptionexpands it to 6 senses:

Free tier: 50 analyses/day, no credit card required.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Create crafted UI components inspired by the best 21st.dev design engineers.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

ALAPI MCP Tools,Call hundreds of API interfaces via MCP

AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform

MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.

APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.