This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Zero-dependency sovereign personal agent skill for non-invasive evaluation of Medial Olivocochlear (MOC) Efferent Contralateral Suppression of Otoacoustic Emissions (CAS-OAE), speech-in-noise gating, and auditory protective resilience.
flowchart TD
BaselineOAE["Baseline Otoacoustic Emission Recording (DPOAE / TEOAE)"] --> NoiseCondition["Contralateral Broadband Noise Stimulation (60-65 dB SPL)"]
NoiseCondition --> SOC_MOC["Superior Olivary Complex Medial Olivocochlear Bundle Activation"]
SOC_MOC --> OHCDamp["Cochlear Outer Hair Cell Somatic Electromotility Damping"]
OHCDamp --> DeltaAmp["Contralateral Suppression Magnitude (Delta Amp in dB)"]
DeltaAmp --> AuditoryGating["Auditory Speech-in-Noise Gating & Acoustic Guarding Engine"]
AuditoryGating --> Agent["OpenClaw / Hermes Personal Agent Sound Shaping"]Deterministic Math: Pure Python standard library implementation with zero external dependencies.
Auditory Neurophysiology Standards: Formulates contralateral acoustic stimulation suppression, baseline signal-to-noise gating, and MOC gain reduction.
Cocktail Party Problem & Listening Fatigue: Identifies subclinical central auditory processing deficits in noisy environments.
Model Context Protocol (MCP): Native JSON-RPC tool integration for LLMs and autonomous agents.
Related MCP server: Auditory Binaural Masking Level Difference (BMLD) MCP Server
from client import AcousticEfferentSuppressionClient
client = AcousticEfferentSuppressionClient()
result = client.evaluate_contralateral_suppression(
baseline_oae_amplitude_db_spl=11.2,
noise_conditioned_oae_amplitude_db_spl=9.4,
contralateral_noise_db_spl=65.0
)
print("Suppression Magnitude:", result["suppression_magnitude_db"], "dB")
print("Efferent Score:", result["efferent_gating_score"])
print("Classification:", result["classification"])Apache-2.0
Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.
Deterministic eligibility scoring for AI agents: CLEAR/HOLD/FAIL verdicts, published weights.
Agent verification tools: CSV quality, citation checks, AI-readiness audits, requirement extraction
49 deterministic tools for text integrity, agent control, and contextual quality evidence.
