# Audio Calibration MCP (mcpb · audio-calibration-mcp-0.2.0-beta.1.mcpb)

Evidence-bound REW measurement, analysis, conservative EQ, DSP, and listening-test tools.

- Trust score: 48/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- mcpb · `audio-calibration-mcp-0.2.0-beta.1.mcpb`: 48/100 (this document), [markdown](https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1.md), [page](https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/daredoole/audio-calibration-mcp/releases/download/v0.2.0-beta.1/audio-calibration-mcp-0.2.0-beta.1.mcpb`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 13/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 23 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 6297 tokens (~60/item across 104 items; 104 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 21 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "rew_launch_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 104 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

- Download bundle: `https://github.com/daredoole/audio-calibration-mcp/releases/download/v0.2.0-beta.1/audio-calibration-mcp-0.2.0-beta.1.mcpb`

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 45, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 44, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 43, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 42, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 41, +4)

- [functional improvement] Stability: unverified → 0.27

## MCP tools (104)

### `audio_job_status` (~37 tokens)

Poll an asynchronous analysis job without holding an MCP request open.

Input parameters:

- `includeResult` (boolean)
- `jobId` (string, required)

### `audio_job_cancel` (~35 tokens)

Cancel or suppress the result of an asynchronous analysis job.

Input parameters:

- `confirm` (boolean)
- `jobId` (string, required)

### `audio_doctor` (~38 tokens)

Check Node, workspace, REW, host audio, JamesDSP, and configured DSP adapters without changing state.

Input parameters:

- `home` (string)

### `rew_install_discover` (~46 tokens)

Find a local REW installation across Windows, macOS, and Linux. An explicit absolute executable path can be supplied when automatic discovery fails.

Input parameters:

- `executablePath` (string)

### `rew_launch_plan` (~55 tokens)

Create a hash-bound plan to start REW when its local API is offline. Uses automatic discovery or an explicit user-supplied executable path.

Input parameters:

- `executablePath` (string)
- `startupTimeoutSeconds` (integer)

### `rew_launch_execute` (~55 tokens)

Start the exact discovered REW executable after explicit confirmation, then verify that the API becomes ready on port 4735.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_capability_negotiate` (~31 tokens)

Detect the live REW API/version and supported read-only command surfaces before a workflow uses them.

### `audio_artifact_validate` (~29 tokens)

Validate a versioned calibration artifact and report reproducibility gaps.

Input parameters:

- `artifact` (object, required)

### `audio_artifact_migrate` (~32 tokens)

Migrate a legacy calibration artifact to the current schema without writing files.

Input parameters:

- `artifact` (object, required)

### `audio_artifact_create` (~66 tokens)

Create and validate a versioned, replayable calibration artifact from supplied evidence.

Input parameters:

- `analyses` (object)
- `filters` (array)
- `provenance` (object)
- `session` (object, required)
- `sweeps` (array)
- `verification`

### `audio_session_replay_validate` (~43 tokens)

Validate whether a calibration artifact and its saved measurement bytes have enough immutable evidence for deterministic replay.

Input parameters:

- `artifact` (object, required)
- `home` (string)

### `audio_support_bundle_plan` (~54 tokens)

Create a hash-bound plan for a redacted JSON support artifact; raw traces and identifying metadata are omitted.

Input parameters:

- `home` (string)
- `outputName` (string, required)
- `sourceFile` (string, required)

### `audio_support_bundle_execute` (~46 tokens)

Write an exact redacted support artifact after rechecking its source hash.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_dsp_adapter_capabilities` (~28 tokens)

Inspect cross-platform DSP export/apply adapters and the explicit configuration needed for each.

### `audio_dsp_apply_plan` (~43 tokens)

Preview and hash-bind an exact Equalizer APO or dedicated CamillaDSP filter-file change.

Input parameters:

- `adapter` (string, required)
- `filters` (array, required)

### `audio_dsp_apply_execute` (~51 tokens)

Back up, apply, verify, and roll back an exact configured DSP filter-file plan.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_uncertainty_budget` (~45 tokens)

Propagate calibrated measurement uncertainty using GUM-style linear combination and an explicit standards-claim boundary.

Input parameters:

- `components` (array, required)
- `coverageProbability` (number)

### `audio_uncertainty_monte_carlo` (~64 tokens)

Propagate normal, rectangular, and triangular input uncertainties with deterministic JCGM-101-style Monte Carlo sampling.

Input parameters:

- `components` (array, required)
- `estimate` (number)
- `seed` (integer)
- `trials` (integer)

### `audio_repeatability_bootstrap` (~46 tokens)

Estimate repeatability and a deterministic bootstrap confidence interval from repeated scalar measurements.

Input parameters:

- `seed` (integer)
- `trials` (integer)
- `values` (array, required)

### `audio_transfer_quality` (~118 tokens)

Evaluate complex transfer-function coherence, phase confidence, harmonic contamination, excitation, timing variance, and clock drift.

Input parameters:

- `bins` (array, required)
- `maximumClockDriftPpm` (number)
- `maximumHarmonicContaminationDb` (number)
- `maximumPhaseUncertaintyDeg` (number)
- `minimumCoherence` (number)
- `minimumInputPower` (number)
- `minimumValidFraction` (number)
- `repeatElapsedSeconds` (array)
- `repeatTimingSeconds` (array)

### `audio_room_metrics` (~74 tokens)

Calculate EDT, T20/T30, C50/C80, D50, center time, decay linearity, and regression uncertainty from an impulse response.

Input parameters:

- `directIndex` (integer)
- `impulse` (array, required)
- `minimumDecayRSquared` (number)
- `sampleRateHz` (integer, required)

### `audio_room_spatial_summary` (~31 tokens)

Summarize position-to-position variance for room-acoustic metrics.

Input parameters:

- `positions` (array, required)

### `audio_speech_transmission_screening` (~53 tokens)

Calculate an IEC-60268-16-inspired speech-transmission screen from caller-supplied modulation transfer factors and importance weights.

Input parameters:

- `bands` (array, required)
- `redundancyPenalty` (number)

### `audio_polar_characterization` (~39 tokens)

Analyze guided loudspeaker polar scans and produce exploratory directivity rows with a CTA-2034 claim boundary.

Input parameters:

- `angles` (array, required)

### `audio_maximum_clean_output` (~57 tokens)

Evaluate a protected level ladder for output compression, coherence loss, and limiting using AES75-inspired gates.

Input parameters:

- `levelRuns` (array, required)
- `maximumCompressionDb` (number)
- `minimumCoherence` (number)

### `audio_multisource_optimize` (~79 tokens)

Solve regularized complex multi-source weights across training seats and require held-out-seat evaluation before acceptance.

Input parameters:

- `heldOutMatrices` (array)
- `iterations` (integer)
- `maxGainDb` (number)
- `regularization` (number)
- `targets` (array, required)
- `trainMatrices` (array, required)

### `audio_multisource_physical_optimize` (~81 tokens)

Coordinate-search bounded gain, delay, polarity, and fixed crossover controls across training seats with held-out verification.

Input parameters:

- `constraints` (array, required)
- `frequenciesHz` (array, required)
- `heldOutMatrices` (array)
- `passes` (integer)
- `targets` (array, required)
- `trainMatrices` (array, required)

### `audio_fir_design` (~94 tokens)

Design a regularized bounded mixed-phase FIR proposal and report causality, pre-ringing, latency, quantization, and deployment gates.

Input parameters:

- `latencySamples` (integer)
- `maxBoostDb` (number)
- `measuredResponse` (array, required)
- `quantizationBits` (integer)
- `regularization` (number)
- `taps` (integer)
- `targetResponse` (array, required)

### `audio_laboratory_listening_plan` (~77 tokens)

Create blinded randomized MUSHRA- or BS.1116-inspired trials with hidden-reference and anchor readiness gates.

Input parameters:

- `excerpts` (array)
- `listeners` (integer)
- `method` (string, required)
- `seed` (string)
- `systems` (array, required)
- `trials` (integer)

### `audio_laboratory_listening_report` (~40 tokens)

Produce descriptive confidence and repeatability statistics for completed controlled listening trials.

Input parameters:

- `plan` (object, required)
- `responses` (array, required)

### `audio_spatial_layout_assessment` (~53 tokens)

Preflight immersive channel coordinates and head-position metadata without overstating BS.2051 compliance.

Input parameters:

- `channels` (array, required)
- `headPositionMetadata` (object)
- `listener` (object)

### `audio_sofa_metadata_assessment` (~44 tokens)

Preflight HRTF/BRIR SOFA metadata before handing the HDF5 file to a maintained SOFA implementation.

Input parameters:

- `metadata` (object, required)

### `audio_evaluation_corpus_manifest` (~69 tokens)

Audit synthetic, external, loopback, and cross-tool reference artifacts for hashes, licenses, independence, provenance, and regression tolerances.

Input parameters:

- `crossTool` (array)
- `external` (array)
- `loopbacks` (array)
- `synthetic` (array)

### `audio_dataset_catalog` (~34 tokens)

List curated independent audio datasets with DOI, institution, license, measurement metadata, pinned artifact size, and checksum without downloading anything.

### `audio_dataset_download_plan` (~65 tokens)

Create a hash-bound plan for one pinned licensed dataset artifact. No download occurs until the matching execute tool is explicitly confirmed.

Input parameters:

- `datasetId` (string, required)
- `home` (string)
- `licenseAccepted` (boolean)
- `maximumBytes` (integer, required)

### `audio_dataset_download_execute` (~73 tokens)

Download one exact planned dataset artifact, enforce the byte ceiling, verify its pinned upstream checksum, calculate SHA-256, and write a provenance receipt without overwriting files.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)
- `timeoutMs` (integer)

### `audio_capabilities` (~26 tokens)

Report platform, safety limits, REW endpoint, targets, and optional integration support.

### `audio_workspace_scan` (~33 tokens)

Inventory profiles, sessions, measurements, backups, and reports in the AudioCalibration workspace.

Input parameters:

- `home` (string)

### `audio_host_inventory` (~19 tokens)

Read host audio devices and defaults without changing routing.

### `audio_route_plan` (~60 tokens)

Create a hash-bound host audio routing plan. Native mutation is currently supported only through pactl on Linux.

Input parameters:

- `sink` (string)
- `sinkMuted` (boolean)
- `source` (string)
- `sourceMuted` (boolean)

### `audio_route_execute` (~46 tokens)

Apply an exact host routing plan, verify it, and return rollback values.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_probe` (~27 tokens)

Check the local REW API and inventory live measurements.

Input parameters:

- `timeoutMs` (integer)

### `rew_audio_inventory` (~28 tokens)

Inspect REW driver, devices, channels, sample rate, and microphone calibration without changing anything.

### `rew_audio_configure_plan` (~90 tokens)

Create a hash-bound REW input/output configuration plan while preserving the current microphone calibration.

Input parameters:

- `driver` (string)
- `input` (string)
- `inputChannel` (string)
- `inputDevice` (string)
- `output` (string)
- `outputChannel` (string)
- `outputDevice` (string)
- `sampleRateHz` (integer)

### `rew_audio_configure_execute` (~54 tokens)

Apply and verify an exact REW audio configuration plan; restore the microphone calibration if REW clears it.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_input_level_check` (~39 tokens)

Capture microphone input levels for a bounded period. This emits no sweep.

Input parameters:

- `confirm` (boolean)
- `durationMs` (integer)

### `rew_measurement_plan` (~131 tokens)

Create a guarded generic REW sweep plan for general speakers, cars, or laptops.

Input parameters:

- `deviceClass` (string, required)
- `endHz` (number)
- `home` (string)
- `levelDbfs` (number)
- `maxSplDb` (number)
- `outputChannels` (array, required)
- `repetitions` (integer)
- `saveFile` (string, required)
- `startHz` (number)
- `sweepLength` (string)
- `targetId` (string)
- `timingReference` (string)
- `titlePrefix` (string, required)

### `rew_repeated_session_plan` (~145 tokens)

Plan 4-6 separately retained left, right, and combined traces with a complete route, volume, DSP, microphone, preset, and sweep fingerprint.

Input parameters:

- `channels` (array, required)
- `deviceClass` (string, required)
- `endHz` (number)
- `home` (string)
- `levelDbfs` (number)
- `maxSplDb` (number)
- `repeats` (integer)
- `saveFile` (string, required)
- `startHz` (number)
- `sweepLength` (string)
- `targetId` (string)
- `timingReference` (string)
- `titlePrefix` (string, required)

### `rew_level_ladder_plan` (~131 tokens)

Plan protected separately retained distortion/compression sweeps at several levels for one channel.

Input parameters:

- `deviceClass` (string, required)
- `endHz` (number)
- `home` (string)
- `levelsDbfs` (array, required)
- `maxSplDb` (number)
- `outputChannel` (string, required)
- `role` (string, required)
- `saveFile` (string, required)
- `startHz` (number)
- `sweepLength` (string)
- `targetId` (string)
- `timingReference` (string)
- `titlePrefix` (string, required)

### `rew_measurement_execute` (~75 tokens)

Run an exact protected sweep plan, label and save results, then restore REW state. Audible confirmation and physical readiness flags are mandatory.

Input parameters:

- `areaClear` (boolean)
- `confirm` (boolean)
- `confirmationToken` (string, required)
- `micPlaced` (boolean)
- `plan` (object, required)

### `rew_measurement_cancel` (~24 tokens)

Cancel a live REW measurement.

Input parameters:

- `confirm` (boolean)

### `rew_save_all` (~49 tokens)

Compatibility alias: create a hash-bound Save-all plan; execute with rew_save_all_execute.

Input parameters:

- `home` (string)
- `note` (string)
- `saveFile` (string, required)

### `rew_save_all_plan` (~51 tokens)

Create a hash-bound plan to save all live REW measurements into a new workspace MDAT.

Input parameters:

- `home` (string)
- `note` (string)
- `saveFile` (string, required)

### `rew_save_all_execute` (~49 tokens)

Execute and verify an exact REW Save-all plan without overwriting an existing artifact.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_load_file` (~43 tokens)

Compatibility alias: create a hash-bound workspace MDAT load plan; execute with rew_load_file_execute.

Input parameters:

- `file` (string, required)
- `home` (string)

### `rew_load_file_plan` (~40 tokens)

Create a hash-bound plan to load a workspace-contained MDAT into REW.

Input parameters:

- `file` (string, required)
- `home` (string)

### `rew_load_file_execute` (~45 tokens)

Load the exact hashed MDAT into REW after explicit confirmation.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_trace` (~58 tokens)

Fetch a bounded REW magnitude/phase, group-delay, distortion, RT60, or impulse trace.

Input parameters:

- `id` (string, required)
- `kind` (string, required)
- `ppo` (integer)
- `smoothing` (string)

### `rew_generate_trace` (~53 tokens)

Compatibility alias: create an allowlisted hash-bound derived-trace plan; execute with rew_generate_trace_execute.

Input parameters:

- `measurementIndices` (array, required)
- `parameters` (object)
- `processName` (string, required)

### `rew_generate_trace_plan` (~46 tokens)

Create an allowlisted hash-bound REW derived-trace plan.

Input parameters:

- `measurementIndices` (array, required)
- `parameters` (object)
- `processName` (string, required)

### `rew_generate_trace_execute` (~48 tokens)

Execute an exact derived-trace plan after rechecking the REW measurement set.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_crossover_analysis` (~63 tokens)

Analyze phase agreement and predicted summation around a crossover. Verify the conclusion with a measured combined trace.

Input parameters:

- `crossoverHz` (number, required)
- `mainId` (string, required)
- `spanOctaves` (number)
- `subId` (string, required)

### `rew_multiseat_analysis` (~71 tokens)

Analyze multi-seat consistency, modal candidates, seat outliers, and optional Schroeder frequency.

Input parameters:

- `highHz` (number)
- `ids` (array, required)
- `lowHz` (number)
- `roomVolumeM3` (number)
- `rt60Seconds` (number)

### `audio_eq_proposal` (~86 tokens)

Create conservative cut-first parametric EQ suggestions from a live REW trace; this never applies filters.

Input parameters:

- `bands` (integer)
- `deviceClass` (string, required)
- `highHz` (number)
- `id` (string, required)
- `lowHz` (number)
- `maxBoostDb` (number)
- `maxCutDb` (number)

### `rew_dual_resolution_analysis` (~95 tokens)

Return raw/minimally smoothed and ERB-perceptual views so narrow engineering defects remain separate from broad listening interpretation.

Input parameters:

- `highHz` (number)
- `id` (string, required)
- `lowHz` (number)
- `modalBoundaryHz` (number)
- `smoothingTransitionHz` (number)
- `stepErb` (number)
- `widthErb` (number)

### `rew_direct_late_analysis` (~94 tokens)

Separate direct-window and later reflected impulse energy without treating the chosen gate as universal.

Input parameters:

- `directWindowMs` (number)
- `highHz` (number)
- `id` (string, required)
- `lateWindowMs` (number)
- `lowHz` (number)
- `ppo` (integer)
- `prePeakMs` (number)
- `sampleRateHz` (integer)

### `audio_target_registry` (~28 tokens)

List versioned, evidence-labelled listening target starting points.

Input parameters:

- `deviceClass` (string)

### `audio_evidence_registry` (~23 tokens)

List authoritative sources and exact claim boundaries used by the analysis engine.

### `audio_guided_session_plan` (~78 tokens)

Create a hash-bound guided or expert calibration workflow without changing audio state.

Input parameters:

- `deviceClass` (string, required)
- `home` (string)
- `measurementProfile` (string)
- `mode` (string)
- `name` (string, required)
- `outputChannels` (array)
- `targetId` (string)

### `audio_guided_session_execute` (~52 tokens)

Open an exact guided session record and return its safe next step; this does not emit audio.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_session_status` (~32 tokens)

Read a workspace-contained guided calibration session.

Input parameters:

- `home` (string)
- `sessionFile` (string, required)

### `audio_session_advance_plan` (~56 tokens)

Bind completion of the current guided stage to concise evidence without changing the session.

Input parameters:

- `completedStage` (string, required)
- `evidence` (object, required)
- `home` (string)
- `sessionFile` (string, required)

### `audio_session_advance_execute` (~51 tokens)

Advance one exact guided stage, preserving a recoverable session backup and returning the next tools.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `rew_measurement_quality` (~108 tokens)

Gate live REW traces on coverage, clipping, SNR, repeatability, route state, DSP state, and microphone-calibration identity.

Input parameters:

- `entries` (array, required)
- `expectedTraceCount` (integer)
- `highHz` (number)
- `lowHz` (number)
- `minSnrDb` (number)
- `protectedEvidenceToken` (string, required)
- `requireMicrophoneCalibration` (boolean)
- `requireSnr` (boolean)

### `rew_human_listening_assessment` (~116 tokens)

Start a cancellable asynchronous multidimensional listening assessment; poll audio_job_status for the result.

Input parameters:

- `crossoverHz` (number)
- `deviceClass` (string, required)
- `entries` (array, required)
- `highHz` (number)
- `lowHz` (number)
- `minSnrDb` (number)
- `qualityEvidenceToken` (string, required)
- `requireMicrophoneCalibration` (boolean)
- `requireSnr` (boolean)
- `targetId` (string)

### `audio_eq_design_plan` (~149 tokens)

Create a hash-bound, cut-only EQ proposal trained on stable traces and checked against withheld traces.

Input parameters:

- `deviceClass` (string, required)
- `entries` (array, required)
- `highHz` (number)
- `lowHz` (number)
- `maxCutDb` (number)
- `maxFilters` (integer)
- `maxQ` (number)
- `maxSpatialSpreadDb` (number)
- `minCorrectionDb` (number)
- `minValidationImprovementDb` (number)
- `qualityEvidenceToken` (string, required)
- `sampleRateHz` (integer)
- `targetId` (string)
- `validationCount` (integer)

### `audio_linked_stereo_eq_plan` (~199 tokens)

Create regularized per-channel EQ with linked filter centers and bounded left/right gain differences; each channel must pass held-out validation independently.

Input parameters:

- `deviceClass` (string, required)
- `highHz` (number)
- `leftEntries` (array, required)
- `leftQualityEvidenceToken` (string, required)
- `lowHz` (number)
- `maxCutDb` (number)
- `maxFilters` (integer)
- `maxInterchannelGainDeltaDb` (number)
- `maxQ` (number)
- `maxSpatialSpreadDb` (number)
- `minCorrectionDb` (number)
- `minValidationImprovementDb` (number)
- `regularization` (number)
- `rightEntries` (array, required)
- `rightQualityEvidenceToken` (string, required)
- `sampleRateHz` (integer)
- `targetId` (string)
- `validationCount` (integer)

### `audio_speaker_protection_assessment` (~117 tokens)

Derive correction floor and permitted boost only from supplied capability, headroom, compression, and limiter evidence.

Input parameters:

- `compressionDb` (number)
- `continuousSplDb` (number)
- `headroomDb` (number)
- `limiterObserved` (boolean)
- `manufacturerF3Hz` (number)
- `maximumBoostDb` (number)
- `measuredF3Hz` (number)
- `measuredMaxCleanSplDb` (number)
- `minimumCorrectionHz` (number)

### `rew_compression_analysis` (~40 tokens)

Analyze a matched REW sweep-level ladder for frequency-dependent output compression.

Input parameters:

- `entries` (array, required)
- `levelsDbfs` (array, required)

### `audio_post_eq_verification` (~169 tokens)

Accept or reject an EQ using separately measured before/after traces, matched state fingerprints, level match, quality gates, and repeatability.

Input parameters:

- `afterEntries` (array, required)
- `afterQualityEvidenceToken` (string, required)
- `beforeEntries` (array, required)
- `beforeQualityEvidenceToken` (string, required)
- `deviceClass` (string, required)
- `highHz` (number)
- `levelMatchHighHz` (number)
- `levelMatchLowHz` (number)
- `levelMatchToleranceDb` (number)
- `lowHz` (number)
- `maximumRepeatabilityRegressionDb` (number)
- `minimumTonalImprovementDb` (number)
- `requireMicrophoneCalibration` (boolean)
- `targetId` (string)

### `rew_diagnostic_capabilities` (~34 tokens)

Read the live REW SPL, RTA, stepped-measurement, and generator command surfaces without running them.

### `rew_diagnostic_plan` (~44 tokens)

Bind an exact command exposed by the live REW diagnostic API.

Input parameters:

- `command` (string, required)
- `endpoint` (string, required)
- `parameters` (object)

### `rew_diagnostic_execute` (~57 tokens)

Execute an exact live REW diagnostic plan; audible operations require physical-readiness confirmation.

Input parameters:

- `audibleReady` (boolean)
- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_filter_export_plan` (~48 tokens)

Create a hash-bound cross-platform filter export plan.

Input parameters:

- `file` (string, required)
- `filters` (array, required)
- `format` (string, required)
- `home` (string)

### `audio_filter_export_execute` (~42 tokens)

Write and verify an exact cross-platform filter export.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_listening_test_plan` (~123 tokens)

Create a fingerprinted, measured-level-matched randomized A/B or ABX listening-test plan.

Input parameters:

- `levelMatchedWithinDb` (number)
- `measuredLevelDifferenceDb` (number)
- `mode` (string)
- `playbackChainFingerprint` (string)
- `presetA` (string, required)
- `presetB` (string, required)
- `presetFingerprintA` (string)
- `presetFingerprintB` (string)
- `programExcerpts` (array)
- `seed` (string)
- `trials` (integer)

### `audio_listening_test_report` (~40 tokens)

Summarize a completed listening test while keeping preference separate from objective quality.

Input parameters:

- `plan` (object, required)
- `responses` (array, required)

### `jamesdsp_ab_plan` (~98 tokens)

Create a hash-bound randomized JamesDSP A/B plan with measured host-volume compensation and an exact restore target.

Input parameters:

- `home` (string)
- `levelMatchToleranceDb` (number)
- `measuredLevelDifferenceDb` (number, required)
- `presetA` (string, required)
- `presetB` (string, required)
- `programExcerpts` (array, required)
- `seed` (string)
- `trials` (integer)

### `jamesdsp_ab_present_execute` (~64 tokens)

Present one blinded, randomized, level-matched JamesDSP A/B sample with transactional rollback.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)
- `sample` (required)
- `trial` (integer, required)

### `jamesdsp_ab_restore_execute` (~52 tokens)

Restore the exact JamesDSP preset and host volume captured by a JamesDSP A/B plan.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `audio_report_plan` (~153 tokens)

Create a hash-bound Markdown, HTML, JSON, and optional standalone before/after SVG report plan.

Input parameters:

- `assessment` (object, required)
- `baseName` (string, required)
- `comparisonGroups` (array)
- `comparisonSubtitle` (string)
- `eq` (object)
- `home` (string)
- `levelMatchHighHz` (number)
- `levelMatchLowHz` (number)
- `listening` (object)
- `modalBoundaryHz` (number)
- `resolutionHighHz` (number)
- `resolutionLowHz` (number)
- `resolutionMeasurementId` (string)
- `smoothingTransitionHz` (number)
- `title` (string)

### `audio_report_execute` (~45 tokens)

Write and verify an exact human-readable and machine-readable calibration report set.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `speaker_profile_save` (~44 tokens)

Deprecated compatibility alias: create a hash-bound speaker-profile save plan; execute it with speaker_profile_save_execute.

Input parameters:

- `home` (string)
- `profile` (object, required)

### `speaker_profile_save_plan` (~37 tokens)

Create a hash-bound evidence-tagged speaker-profile save/update plan.

Input parameters:

- `home` (string)
- `profile` (object, required)

### `speaker_profile_save_execute` (~47 tokens)

Save an exact speaker profile with pre-change backup, verification, and rollback.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `speaker_profile_get` (~29 tokens)

Read a workspace speaker profile.

Input parameters:

- `home` (string)
- `id` (string, required)

### `car_channel_map_validate` (~40 tokens)

Validate a car-audio DSP channel map and flag missing protective crossovers, duplicate outputs, and invalid passbands.

Input parameters:

- `channels` (array, required)

### `car_geometric_delay_advisor` (~55 tokens)

Calculate a geometry-only initial delay map for car speakers. Acoustic measurements supersede this estimate.

Input parameters:

- `listener` (object, required)
- `speakers` (array, required)
- `speedOfSoundMps` (number)

### `jamesdsp_status` (~36 tokens)

Detect JDSP4Linux and decode engine, master-bypass, EQ-module, runtime-sync, and active-preset identity state.

### `jamesdsp_snapshot` (~33 tokens)

Fingerprint the live JamesDSP configuration and identify the exact active preset and effective EQ/bypass state without changing anything.

### `jamesdsp_preset_plan` (~48 tokens)

Create a hash-bound JamesDSP preset operation with an automatic configuration backup.

Input parameters:

- `action` (string, required)
- `home` (string)
- `presetName` (string, required)

### `jamesdsp_preset_execute` (~59 tokens)

Back up JamesDSP, execute an exact preset load/save plan, verify status, and automatically restore the active configuration on failure.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

### `jamesdsp_key_plan` (~51 tokens)

Create a hash-bound change for one JamesDSP key after verifying that the installed version exposes it.

Input parameters:

- `home` (string)
- `key` (string, required)
- `value` (string, required)

### `jamesdsp_key_execute` (~56 tokens)

Back up JamesDSP, apply one exact key change, verify it, and automatically restore the active configuration on failure.

Input parameters:

- `confirm` (boolean)
- `confirmationToken` (string, required)
- `plan` (object, required)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1#diagnostics

## Score history

- 2026-09-20: 48
- 2026-09-19: 48
- 2026-09-18: 47
- 2026-09-17: 47
- 2026-09-16: 47
- 2026-09-15: 46
- 2026-09-14: 46
- 2026-09-13: 45
- 2026-09-12: 45
- 2026-09-11: 44
- 2026-09-10: 44
- 2026-09-09: 43
- 2026-09-08: 43
- 2026-09-07: 42
- 2026-09-06: 42
- 2026-09-05: 41
- 2026-09-04: 41
- 2026-09-03: 37
- 2026-09-02: 37
- 2026-09-01: 37
- 2026-08-31: 37
- 2026-08-30: 37
- 2026-08-29: 37
- 2026-08-28: 37
- 2026-08-27: 37

## Common questions

### What is the Audio Calibration MCP server?

Audio Calibration MCP is listed in the public MCP registry as io.github.daredoole/audio-calibration-mcp. Evidence-bound REW measurement, analysis, conservative EQ, DSP, and listening-test tools. This page covers its MCPB bundle (https://github.com/daredoole/audio-calibration-mcp/releases/download/v0.2.0-beta.1/audio-calibration-mcp-0.2.0-beta.1.m…).

### Is the Audio Calibration MCP server safe to use?

Audio Calibration MCP scores 48 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Audio Calibration MCP server expose?

Audio Calibration MCP exposes 104 tools: audio_job_status, audio_job_cancel, audio_doctor, rew_install_discover, rew_launch_plan, and 99 more. Their descriptions and schemas cost roughly 6,297 tokens of context every time the server is loaded.

### What licence is the Audio Calibration MCP server under?

Audio Calibration MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/daredoole/audio-calibration-mcp
- Changelog RSS feed: https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1.xml
- Changelog JSON feed: https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1.json
- HTML version of this page: https://verifymcp.io/servers/daredoole-audio-calibration-mcp/https-github-com-daredoole-audio-calibration-mcp-releases-download-v0-2-0-beta-1