# io.github.daredoole/evoburrow-mcp Unofficial guarded A1 Evo AcoustiX, REW, and Denon/Marantz calibration tools. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the content rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 2.0.0-beta.1 - **Author:** io.github.daredoole - **License:** Unknown - **Source:** https://github.com/daredoole/evoburrow-mcp ## Trust 60/100 (B), scored on the content rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: clean - Obfuscation scan: clean - Evidence age: 0 days ## Security scan - **Status:** clean - **Scanned:** 2026-09-26T17:07:41.945Z - **Version scanned:** HEAD - **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it. ## Tools 40 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `a1_terminal_capabilities` — Report guarded terminal workflows and platform support. - `a1_terminal_plan` — Create a hash-bound plan for an A1 transfer or measurement run. - `a1_terminal_execute` — Execute an exact A1 terminal plan. Requires the full plan, its token, and confirm=true. - `receiver_models` — List explicitly profiled Denon/Marantz models and capability confidence. - `speaker_inventory_detect` — Detect configured channels from A1/ADY artifacts and return prompts for physical speaker details the AVR cannot know. - `speaker_profile_save` — Save verified speaker/sub capability profiles. No specification is invented. - `rew_probe` — Check the local REW API and report version/capabilities. - `rew_audio_inventory` — Inspect REW audio readiness, selected devices/channels, calibration file, and available choices without changing anything. - `rew_audio_configure_plan` — Create a confirmation-bound plan to select REW audio driver, devices, channels, and sample rate. - `rew_audio_configure` — Apply an exact REW audio configuration plan. The token and confirm=true are mandatory. - `rew_input_level_check` — Monitor the connected REW microphone for a bounded period and report peak/RMS headroom. Starts capture but emits no sweep. - `rew_post_measurement_plan` — Build a guarded, level-matched post-calibration sweep plan. It can switch Denon Speaker Presets and REW output channels automatically after the microphone and H - `rew_post_measurement_execute` — Execute an exact post-calibration plan: configure safe sweep settings, switch/verify preset, run and label each sweep, save the MDAT, and restore the original p - `rew_measurement_cancel` — Cancel a REW measurement currently in progress. This does not change AVR calibration data. - `rew_save_all` — Save all live REW measurements to a workspace-contained MDAT file. - `rew_load_file` — Load a workspace-contained .mdat into live REW. Explicit confirmation is mandatory. - `rew_generate_trace` — Generate an allowlisted derived trace in live REW from selected measurements. - `rew_trace` — Fetch a bounded live REW trace including magnitude/phase, group delay, distortion, decay/RT60, or impulse. - `rew_crossover_analysis` — Analyze phase agreement and predicted vector summation through a crossover band. - `rew_multiseat_analysis` — Analyze seat consistency, modal clusters, outliers, and estimate Schroeder frequency when room volume and RT60 are supplied. - `denon_decode` — Decode Denon/Marantz text-protocol responses into structured status. - `denon_snapshot` — Read live AVR state and optionally save a workspace backup. - `denon_propose_changes` — Capture and save a baseline, then create a deterministic AVR diff and confirmation token; does not write to the receiver. - `denon_execute_plan` — Apply one exact baseline-bound AVR plan, verify every write, and roll back on partial failure. - `calibration_report_score` — Score ADY, OCA, HTML, live REW, and optional AVR evidence with explicit provenance and missing-data confidence. - `ab_test_plan` — Create a level-matched, preset-tracked A/B protocol without changing the AVR. - `calibration_preset_catalog` — Discover, hash, deduplicate, and describe generated A1 OCA calibrations without assigning device slots. - `calibration_preset_propose_binding` — Propose binding one exact OCA artifact hash to Denon Speaker Preset 1 or 2; does not write or control the AVR. - `calibration_preset_commit_binding` — Commit an exact proposed preset binding to the workspace registry. Requires matching token and confirm=true. - `calibration_preset_status` — Join the local calibration registry with read-only live AVR context, including the active Speaker Preset when supported. - `denon_speaker_preset_audit` — Recall Denon Speaker Presets while muted, capture their Audyssey processing state, and restore the exact baseline. - `denon_quick_select_audit` — Safely recall selected Denon Quick Select slots while muted, capture their state, and restore the exact baseline. State-changing recalls require explicit confir - `rew_install_discover` — Find a local REW installation across Windows, macOS, and Linux without starting it. - `rew_launch_plan` — Create a hash-bound plan to start the exact discovered REW executable. - `rew_launch_execute` — Start the exact planned REW executable after explicit confirmation and verify its local API. - `rew_capability_negotiate` — Probe the live REW API and report which read-only command surfaces are available. - `a1_workspace_scan` — Inventory A1 Evo artifacts without modifying them. - `a1_inspect_artifact` — Inspect an ADY, AVR, OCA, target-curve, HTML report, or session log with bounded output. - `a1_analyze_measurements` — Analyze ADY impulse responses: timing, polarity, RMS/crest factor, and broad-band spectral balance. Interpretations are flagged separately. - `a1_compare_calibrations` — Compare two OCA calibration exports channel by channel. ## Install This entry has no npm package and no hosted endpoint, so there is nothing for an MCP client to launch or connect to. It is indexed as source only. ## Blast radius Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs commands; 4 privileged tools. - Floor 37, ceiling 77 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.daredoole%2Fevoburrow-mcp - Install plan: https://forgeregistry.com/api/v1/packages/io.github.daredoole%2Fevoburrow-mcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.daredoole%2Fevoburrow-mcp - HTML page: https://forgeregistry.com/registry/io.github.daredoole%2Fevoburrow-mcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.