web perception
Provides Express middleware to add audio capture endpoints to web applications, enabling the MCP server to tap into the Web Audio graph.
webear
Give your AI real senses — hear, see, and feel any web app.
An MCP server + browser SDK that gives AI coding assistants direct sensory access to a live web application. Audio, visuals, performance, network, security, and console — captured from the browser, analyzed in real time, delivered via MCP.
"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.

What It Does
Tool | Description |
| Record a short clip (500ms–30s) of what your web app is outputting right now |
| Signal analysis: RMS, peak dB, clipping, spectral centroid, frequency bands, BPM, timing jitter |
| Plain-English AI description — "the kick is boomy with heavy sub buildup around 80 Hz" |
| Compare two captures and flag what changed — loudness, tone, timing, clipping |
Related MCP server: laserbrain
How It Works
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.
Quick Start
1. Install
npm install webear2. 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()Option B — explicit AudioContext
const ctx = new AudioContext()
const masterGain = ctx.createGain()
masterGain.connect(ctx.destination)
WebEar.init({ audioContext: ctx, outputNode: masterGain })Option C — Tone.js project
import * as Tone from 'tone'
WebEar.init({ toneJs: true })Option D — Three.js WebGL Game
import * as THREE from 'three'
const listener = new THREE.AudioListener()
camera.add(listener)
WebEar.init({ tapNode: listener.getInput() })Option E — plain script tag
<script src="node_modules/webear/client-snippet.js"></script>
<script>WebEar.init()</script>4. Configure your IDE
Claude Code (.mcp.json in project root):
{
"mcpServers": {
"webear": {
"command": "npx",
"args": ["webear"],
"env": {
"WEBEAR_BASE_URL": "http://localhost:5000",
"CODEDSWITCH_API_KEY": "your-key-here"
}
}
}
}Cursor (.cursor/mcp.json):
{
"mcpServers": {
"webear": {
"command": "npx",
"args": ["webear"],
"env": {
"WEBEAR_BASE_URL": "http://localhost:5000",
"CODEDSWITCH_API_KEY": "your-key-here"
}
}
}
}Windsurf (mcp_config.json):
{
"webear": {
"command": "npx",
"args": ["webear"],
"disabled": false,
"env": {
"WEBEAR_BASE_URL": "http://localhost:5000",
"CODEDSWITCH_API_KEY": "your-key-here"
}
}
}5. Get an API key
Get your free CODEDSWITCH_API_KEY at codedswitch.com.
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?"
Example Output
analyze_audio
── 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).diff_audio
── 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.Configuration
Environment Variables
Variable | Default | Description |
|
| URL of your dev server (where middleware is mounted) |
| — | API key from codedswitch.com — required for |
|
| Override the analysis API base (advanced / self-hosted) |
Middleware Options
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)
})Client Options
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)
})Requirements
Node.js >= 18
A browser that supports
MediaRecorder(Chrome, Firefox, Edge, Safari 14+)A
CODEDSWITCH_API_KEYfor analysis (free at codedswitch.com)
Who Is This For?
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 with
diff_audioPodcast / 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
Why Not Just Use the Microphone?
Microphone MCPs capture room sound — your fan noise, chair creaks, and room reverb are all in the recording. webear taps the Web Audio API before it hits the DAC, giving you a clean digital signal with no room artifacts.
Web Perception — Full Sensor Suite
WebEar started as audio-only. Web Perception expands it to 6 senses:
Sensor | What it perceives |
WebEar | Audio — mix quality, rhythm, instruments, clipping |
WebEye | Visual — canvas, UI layout, animations, screenshots |
WebSense | Performance — frame rate, memory, audio latency |
WebNerve | Network — API latencies, connection quality, storage |
WebShield | Security — cookies, storage exposure, CSP, framing |
WebLog | Console — logs, warnings, errors, uncaught exceptions |
Install the full browser SDK
import { WebPerception } from 'webear/perception'
WebPerception.init({
apiKey: 'wbr_YOUR_API_KEY',
relayUrl: 'https://www.codedswitch.com',
sensors: ['ear', 'eye', 'sense', 'nerve', 'shield', 'log'],
})Or use a single sensor:
import { WebEar } from 'webear/perception'
WebEar.init({
apiKey: 'wbr_YOUR_API_KEY',
ear: { audioContext: myCtx, audioNode: masterGain },
})Connect via MCP (hosted relay — no local server required)
{
"mcpServers": {
"webear": {
"url": "https://www.codedswitch.com/api/webear/mcp/sse",
"headers": {
"Authorization": "Bearer wbr_YOUR_API_KEY"
}
}
}
}Available MCP Tools
Sensor | Tool | Credits | Description |
Ear |
| Free | Record live tab audio |
Ear |
| 1 | BPM, loudness, frequency bands, clipping, dynamic range |
Ear |
| 2 | AI plain-English description — instruments, genre, mood, mix notes |
Ear |
| 1 | Compare two captures — loudness, tone, timing deltas |
Ear |
| 2 | Grid alignment, swing factor, consistency (0–100%) |
Ear |
| 1 | Capture + analysis in one call |
Ear |
| 3 | Structured mixing feedback |
Eye |
| Free | Record canvas/video from the tab |
Eye |
| 2 | AI visual description — layout, colors, bugs |
Eye |
| 2 | Compare two visual captures |
Sense |
| Free | FPS, memory, layout shifts, audio latency |
Sense |
| 1 | Frame drops, memory pressure, audio underruns |
Nerve |
| Free | API timings, connection quality, storage size |
Nerve |
| 1 | Slow APIs, connection quality, storage bloat |
Shield |
| Free | Cookies, CSP, storage exposure, framing |
Shield |
| 1 | CORS issues, non-HttpOnly cookies, missing CSP |
Log |
| Free | Console output + uncaught exceptions |
Log |
| 1 | Error patterns, stack traces, repeated warnings |
Get an API Key
Sign up at codedswitch.com → Settings → WebEar. Keys start with wbr_.
Contributing
See CONTRIBUTING.md.
License
MIT — see LICENSE
Author
Built by @asume21 — CodedSwitch
This server cannot be installed
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/asume21/webear'
If you have feedback or need assistance with the MCP directory API, please join our Discord server