Skip to main content
Glama
Badajoz95

H-ear MCP Server

by Badajoz95
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

H-ear MCP Server

AI-powered sound classification for Claude. Identify sounds, detect noise events, and classify audio across 7,000+ sound classes — from urban noise to bird species.

H-ear connects Claude to the H-ear World audio classification API via the Model Context Protocol.

Quick Start

npx @h-ear/mcp-server --key YOUR_API_KEY

That's it. Claude now has 14 tools (classification, account, webhooks), a live status resource, and a guided classification prompt.

Related MCP server: soundgrep

Tools

Tool

Auth

Description

classifyAudio

Key

Classify audio from a file or URL. Async submit + poll. Large files auto-chunked.

classifyBatch

Key

Batch classify up to 50 files at once.

listClasses

None

Browse 521+ sound classes across 3 taxonomies (7,000+ including species).

healthCheck

None

API liveness check — status, version, deployment timestamp.

usage

Key

API quota: minutes used, calls today, remaining balance.

listJobs

Key

Recent classification job history with pagination.

getJob

Key

Detailed job result with all detected sound events.

createWebhook

Bearer

Create enterprise webhook with event/taxonomy/tier filters. Returns signing secret once.

listWebhooks

Bearer

List all enterprise webhook registrations.

getWebhook

Bearer

Get webhook details including filter config and delivery stats.

updateWebhook

Bearer

Update webhook URL, events, status (active/paused), or filters.

deleteWebhook

Bearer

Permanently delete a webhook registration.

pingWebhook

Bearer

Send a test.ping event to verify connectivity and signing.

listWebhookDeliveries

Bearer

Delivery audit trail with response status and timing.

Plus:

  • Resource h-ear://status — live API status with taxonomies and class counts

  • Prompt classify-audio — guided workflow with configurable detail level

Supported Audio

Formats

Max Size

Max Duration

MP3, WAV, FLAC, OGG, M4A

25 MB (auto-chunked above)

10 minutes

Files over 25 MB are automatically split into overlapping chunks using ffmpeg, classified in parallel, then merged with deduplication.

Taxonomies

Taxonomy

Classes

Use Case

audioset-yamnet-521

521

General sound classification (default)

audioset-panns-527

527

Extended general classification

species

6,522

Bird species identification

Authentication

Get an API key from h-ear.world (Enterprise plan). Pass it via:

  • Environment variable: HEAR_API_KEY

  • CLI flag: --key YOUR_KEY

  • OAuth 2.1 + PKCE (automatic via claude.ai Connectors Directory — handled by your MCP client)

Two tools (healthCheck, listClasses) work without authentication.

Transport

Transport

Endpoint

stdio (npm)

npx @h-ear/mcp-server --key YOUR_KEY

Streamable HTTP

https://api.h-ear.world/mcp

Documentation

Links

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • soundgrep

    fnsmdehip
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables semantic search of local audio samples by describing sounds, MIDI generation, stem separation, and other music production tools from Claude Desktop.
    2
    MIT

  • waves

    MirrorEdgeAI
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude to analyze and repair audio files by viewing spectrograms, measuring noise, and applying fixes like healing hums or isolating speakers, all with undoable operations and without uploading audio.
    -