H-ear MCP Server
Enables Claude to classify audio across 7,000+ sound classes, including bird species and urban noise, with tools for batch processing, webhooks, and usage tracking.
README
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.
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
- Tool Reference — all 7 tools with schemas and parameters
- Examples — real-world use cases with prompts
- Authentication — API keys, OAuth, Enterprise tiers
- Configuration — Claude Desktop, Claude Code, claude.ai setup
- Troubleshooting — common issues and solutions
Links
- npm: @h-ear/mcp-server
- npm: @h-ear/core
- H-ear World
- OpenClaw Skill (WhatsApp, Telegram, Slack, Discord, Teams)
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.