Give your AI coding assistant ears — capture, analyze, and describe live audio.
Connect Webear to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Give your AI coding assistant ears — capture, analyze, and describe live audio. The webear mcp server is what makes that connection.
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 toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Sensor — ToolEar — capture_audioEye — capture_videoSense — capture_telemetryNerve — capture_nerveShield — capture_shieldLog — capture_logsanalyze_audio — ── Loudness ───────────────────────────────────────── RMS: -12.4 dBFS Peak: -1.2 dBFS Dynamic range: 11.2 dB Crest factor: 3.63 Clipping: nonediff_audio — ── Loudness ────────────────────────────────────────── RMS: -14.2 dBFS → -12.4 dBFS (+1.8 dBFS) ⚠ Peak: -3.1 dBFS → -0.2 dBFS (+2.9 dBFS) ⚠ CLIPPINGBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Configuration is passed through the environment: WEBEAR_BASE_URL, CODEDSWITCH_API_KEY, MCP_API_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
MediaRecorder (Chrome, Firefox, Edge, Safari 14+) - A CODEDSWITCH_API_KEY for analysis (free at codedswitch.com) ---This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Webear's toolset — Sensor, Ear, Eye and 6 more — is a fair guide to whether it matches your workflow. It is maintained by asume21; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Webear's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Sensor | Tool |
| Ear | capture_audio |
| Eye | capture_video |
| Sense | capture_telemetry |
| Nerve | capture_nerve |
| Shield | capture_shield |
| Log | capture_logs |
| analyze_audio | ── Loudness ───────────────────────────────────────── RMS: -12.4 dBFS Peak: -1.2 dBFS Dynamic range: 11.2 dB Crest factor: 3.63 Clipping: none |
| diff_audio | ── 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 |
**Cursor** (`.cursor/mcp.json`):
```json
{
"mcpServers": {
"webear": {
"command": "npx",
"args": ["webear"],
"env": {
"WEBEAR_BASE_URL": "http://localhost:5000",
"CODEDSWITCH_API_KEY": "your-key-here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
MediaRecorder (Chrome, Firefox, Edge, Safari 14+) - A CODEDSWITCH_API_KEY for analysis (free at codedswitch.com) ---| Variable | Description | Required |
|---|---|---|
| WEBEAR_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| CODEDSWITCH_API_KEY | Credential the server authenticates with. | Yes |
| MCP_API_URL | Endpoint or connection string the server talks to. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.