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 Auditory Brainstem Frequency Following Response (FFR) Phase-Locking Value (PLV), SNR, and subcortical temporal envelope encoding fidelity.
flowchart TD
PeriodicSound["Periodic Speech Vowel / Pitch Stimulus (F0 100-300 Hz)"] --> Cochlea["Cochlear Afferent Synchrony & Auditory Nerve Fibers"]
Cochlea --> InferiorColliculus["Upper Brainstem Inferior Colliculus Phase-Locking"]
InferiorColliculus --> FFR_Signal["Continuous Scalp-Recorded FFR Potential (Microvolts)"]
FFR_Signal --> PhaseCoherence["Phase-Locking Value (PLV) & Signal-to-Noise Ratio (SNR)"]
PhaseCoherence --> TemporalScore["Subcortical Auditory Fidelity & Speech-in-Noise Score"]
TemporalScore --> Agent["OpenClaw / Hermes Personal Agent Sound Masking Protection"]Deterministic Math: Pure Python standard library implementation with zero external dependencies.
Auditory Electrophysiology Standards: Implements validated equations for brainstem FFR amplitude, inter-trial phase-locking value (PLV), and stimulus cross-correlation.
Hidden Hearing Loss & Synaptopathy Shield: Sensitive detection of auditory brainstem temporal jitter prior to pure-tone threshold loss.
Model Context Protocol (MCP): Native JSON-RPC tool integration for LLMs and autonomous agents.
Related MCP server: Pupillary Light Reflex MCP Server
from client import AcousticFrequencyFollowingResponseClient
client = AcousticFrequencyFollowingResponseClient()
result = client.evaluate_ffr(
stimulus_fundamental_freq_hz=150.0,
ffr_amplitude_uv=0.42,
phase_locking_value=0.79,
signal_to_noise_ratio_db=9.4
)
print("Phase-Locking Value:", result["phase_locking_value"])
print("Precision Score:", result["subcortical_precision_score"])
print("Classification:", result["classification"])Apache-2.0
This server cannot be deployed
Independent statistical feature evaluation for machine learning and forecasting. ML Referee tests up to 1,000 candidate features in one run against a declared baseline, helping researchers and AI agents decide which inputs to pursue, which bounded feature repairs merit further testing, and where more evidence is needed—without a separate ablation run for every feature. Use the MCP tools to discover input schemas, check access and credits, preflight a dataset, obtain a quote, submit an authorized evaluation, and retrieve structured results and reports. Results are scoped to the submitted evidence and evaluation design; they do not guarantee future model performance. Invite-only beta with manual approval. Public tool discovery requires no authentication; account and evaluation tools require OAuth through approved client connections and available evaluation credits. Connect directly to https://api.mlreferee.com/mcp. Website: https://mlreferee.com Request beta access: https://mlreferee.com/beta Agent setup and documentation: https://mlreferee.com/agents
Analytics for MCP servers. Find out which of your tools agents get wrong. MCPulse shows you which tools AI agents retry, which come back empty, and which they never call at all. Two lines inside your own server. It never sees your arguments or your results. getmcpulse.com
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
135 pay-per-call agent tools: agent intelligence, token risk, developer and AI data tools. x402
