Autoeq Mcp

Created By
verIdyia2 months ago
Overview

AutoEQ MCP Server

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.

한국어 README

What It Does

Ask your AI assistant things like:

  • "Get me the EQ settings for the HD650"
  • "Compare the HE400se and HD600"
  • "Recommend warm-sounding over-ear headphones"
  • "What are the top-ranked IEMs by Harman score?"

The server automatically analyzes frequency response measurements across 8 bands and classifies each headphone's sound signature (Neutral, Warm, Bright, Dark, V-shaped, etc.).

Demo

Headphone comparison with vocal suitability analysis

Comparison demo — HD650 vs DT 990 Pro with per-band chart and vocal recommendation

Finding similar IEMs by sound signature

Similar search demo — finding IEMs with similar tuning using per-band analysis

Tools

ToolDescription
eq_searchSearch by name, type (over-ear/in-ear/earbud), sound signature, or measurement source
eq_profileGet full EQ profile — parametric EQ, fixed band EQ, per-band analysis with visual bars
eq_compareSide-by-side comparison of two headphones across all frequency bands
eq_recommendRecommendations by preference (neutral, warm, bright, bass, vocal, fun, analytical)
eq_rankingHarman headphone listener preference score rankings
eq_targetsList all 61 available target curves (Harman, Diffuse Field, etc.)
eq_syncPull latest data from AutoEQ GitHub and rebuild the database

Example Output

# 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
  ...

Installation

Claude Code / Claude Desktop (stdio)

# 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"
    }
  }
}

SSE Mode (Remote / Multi-client)

# 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

From Source

git clone https://github.com/verIdyia/autoeq-mcp
cd autoeq-mcp
pip install -e .
autoeq-mcp --sync

Configuration

All configuration is via environment variables:

VariableDefaultDescription
AUTOEQ_DATA_DIR~/.autoeq-mcpDirectory for repo clone and SQLite DB
AUTOEQ_MCP_PORT3008SSE server port
AUTOEQ_MCP_HOST0.0.0.0SSE server host
AUTOEQ_MCP_ALLOWED_HOSTS(none)Comma-separated allowed hosts for SSE

Data Source

All headphone data comes from AutoEQ by Jaakko Pasanen (MIT License).

  • 8,800+ headphone/IEM profiles
  • 22 measurement sources (oratory1990, crinacle, Rtings, and more)
  • 61 target curves (Harman 2018/2019, Diffuse Field, etc.)
  • 2,300+ Harman preference scores

The database syncs from the AutoEQ GitHub repository. Run eq_sync or autoeq-mcp --sync to update.

How Sound Signatures Work

The server analyzes each headphone's frequency response error (deviation from target) across 8 bands and classifies it:

SignatureCharacteristics
NeutralAll bands within ±2 dB of target
WarmElevated bass, flat/recessed treble
BrightElevated treble, flat/recessed bass
DarkRecessed treble
V-shapedElevated bass + treble, recessed mids
U-shapedElevated bass + treble
Bass-heavyStrongly elevated bass (>3 dB)
Mid-forwardElevated mids, flat bass/treble
Harman-likeTotal deviation < 1.5 dB average

License

MIT — See LICENSE

Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
verIdyia
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago