loading…
Search for a command to run...
loading…
Headphone/IEM equalization database with 8,800+ models from AutoEQ. Search by name or sound signature, get parametric EQ settings, compare headphones band-by-ba
Headphone/IEM equalization database with 8,800+ models from AutoEQ. Search by name or sound signature, get parametric EQ settings, compare headphones band-by-band, and browse Harman preference score rankings. Includes automatic sound signature classification (Neutral, Warm, Bright, Dark, V-shaped, etc.).
PyPI License: MIT Python 3.10+ Claude Desktop Claude Code claude.ai
pip install autoeq-mcp
An MCP (Model Context Protocol) server that gives AI assistants access to the AutoEQ headphone equalization database — 8,800+ headphones and IEMs with parametric EQ settings, sound signature analysis, and Harman preference scores.
Ask your AI assistant things like:
The server automatically analyzes frequency response measurements across 8 bands and classifies each headphone's sound signature (Neutral, Warm, Bright, Dark, V-shaped, etc.).


| Tool | Description |
|---|---|
eq_search |
Search by name, type (over-ear/in-ear/earbud), sound signature, or measurement source |
eq_profile |
Get full EQ profile — parametric EQ, fixed band EQ, per-band analysis with visual bars |
eq_compare |
Side-by-side comparison of two headphones across all frequency bands |
eq_recommend |
Recommendations by preference (neutral, warm, bright, bass, vocal, fun, analytical) |
eq_ranking |
Harman headphone listener preference score rankings |
eq_targets |
List all 61 available target curves (Harman, Diffuse Field, etc.) |
eq_sync |
Pull latest data from AutoEQ GitHub and rebuild the database |
# Sennheiser HD 650
- Source: oratory1990
- Type: over-ear
- Harman preference score: 84.0
- Sound signature: Neutral, Harman-like
## Per-band analysis (deviation from target, dB)
Sub-bass (20-60Hz): -3.2 dB [·······▓▓▓|··········] sub-bass lacking
Bass (60-250Hz): +0.8 dB [··········|··········] close to target
Mid (500-1kHz): -0.3 dB [··········|··········] close to target
Presence (2k-4kHz): +1.4 dB [··········|▓·········] detail emphasis
Air (8k-20kHz): -2.1 dB [········▓▓|··········] closed / lacking air
## Parametric EQ (Preamp: -6.5 dB)
# Type Fc (Hz) Q Gain (dB)
1 LowShelf 105 0.70 +6.5
2 Peaking 1800 1.20 -2.3
...
# Install
pip install autoeq-mcp
# Initial database sync (clones AutoEQ repo + builds SQLite DB, ~20s)
autoeq-mcp --sync
# Add to Claude Code
claude mcp add autoeq_mcp -- autoeq-mcp
For Claude Desktop, add to your config file:
{
"mcpServers": {
"autoeq": {
"command": "autoeq-mcp"
}
}
}
# Start SSE server
AUTOEQ_MCP_PORT=3008 autoeq-mcp --sse
# With allowed hosts for DNS rebinding protection
AUTOEQ_MCP_ALLOWED_HOSTS="your-domain.com,localhost" autoeq-mcp --sse
git clone https://github.com/verIdyia/autoeq-mcp
cd autoeq-mcp
pip install -e .
autoeq-mcp --sync
All configuration is via environment variables:
| Variable | Default | Description |
|---|---|---|
AUTOEQ_DATA_DIR |
~/.autoeq-mcp |
Directory for repo clone and SQLite DB |
AUTOEQ_MCP_PORT |
3008 |
SSE server port |
AUTOEQ_MCP_HOST |
0.0.0.0 |
SSE server host |
AUTOEQ_MCP_ALLOWED_HOSTS |
(none) | Comma-separated allowed hosts for SSE |
All headphone data comes from AutoEQ by Jaakko Pasanen (MIT License).
The database syncs from the AutoEQ GitHub repository. Run eq_sync or autoeq-mcp --sync to update.
The server analyzes each headphone's frequency response error (deviation from target) across 8 bands and classifies it:
| Signature | Characteristics |
|---|---|
| Neutral | All bands within ±2 dB of target |
| Warm | Elevated bass, flat/recessed treble |
| Bright | Elevated treble, flat/recessed bass |
| Dark | Recessed treble |
| V-shaped | Elevated bass + treble, recessed mids |
| U-shaped | Elevated bass + treble |
| Bass-heavy | Strongly elevated bass (>3 dB) |
| Mid-forward | Elevated mids, flat bass/treble |
| Harman-like | Total deviation < 1.5 dB average |
MIT — See LICENSE
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"veridyia-autoeq-mcp": {
"command": "npx",
"args": []
}
}
}Query your database in natural language
Read-only database access with schema inspection.
Interact with Redis key-value stores.
Database interaction and business intelligence capabilities.