// SCAN REPORT

Orpheus

39 tools. 25 can modify or destroy data without limits.

25 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

25 can modify or destroy data

14 read-only

39 tools total

Community server · catalogue entry verified 02/07/2026

How to control Orpheus ↓

TOOL MAP

What Orpheus exposes to your agents

Read (14) Write / Execute (25) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Orpheus tools

Execute · High explain_style explain_style executes analysis operations on a live music project that depend on the project's audio content and parameters. Execute · Medium play_stop_record This tool executes commands that trigger side effects in REAPER's audio engine. Execute · High apply_changes The description is empty, which significantly lowers confidence. Execute · High apply_master_match The tool renders the master track and applies Matchering spectral analysis/processing against a reference fingerprint.

25 of Orpheus's 39 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Orpheus

PolicyLayer is an MCP gateway — it sits between your AI agents and Orpheus, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add_fx_by_name": {
    "limits": [
      {
        "counter": "add_fx_by_name_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_audio_character": {
    "limits": [
      {
        "counter": "analyze_audio_character_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Orpheus — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ORPHEUS →

Instant setup, no code required.

FULL CATALOGUE

All 39 Orpheus tools

EXECUTE 7 tools

Execute apply_changes apply_changes Execute apply_master_match The spectral half: render the master → Matchering against the fingerprint's Execute build_project_spec Fuse symbolic + audio analysis into one CompositionSpec(current) + a plain-English Execute explain_style "Why does this sound like X?" — run feature thresholds over the current project and Execute play_stop_record Transport control: 'play' | 'stop' | 'record', via Main_OnCommand action IDs. Execute render_and_audit Render, then measure LUFS/spectrum in one call so the agent self-checks Execute render_project Headless render to WAV/MP3 (RENDER_FILE + format/bounds + Main_OnCommand(41824)).

WRITE 18 tools

Write add_fx_by_name add_fx_by_name Write apply_mix_balance fader_db = mix_target(genre, role) − chain_offset(track FX), clamped to fader range. Write constrain_to_key Snap a proposed note set to the nearest in-key pitches before writing. Write create_chord_progression Text chord names ('Cm7, Fm7, Bb7') → voiced, in-key, tempo-correct MIDI. Write create_drum_pattern Step-grid string → GM drum MIDI (kick 36 / snare 38 / hat 42, ch9), humanized. Write create_midi_item Create a MIDI item/take over a bar range; returns a stable take identity. Write create_track Insert a named track and return its stable GUID (one composite bridge call). Write humanize_pass ~12ms timing + 6-velocity jitter on generated MIDI — a cheap, big quality win. Write insert_midi_notes insert_midi_notes Write quantize_notes Quantize a take's notes to a grid (cleanup before/after analysis). Write recommend_changes recommend_changes Write render_stems Render per-track stems by sequential solo — feeds analyze_audio_character. Write set_fx_param Set an FX parameter with name→index resolution (so 'ratio' works, not just index 7). Write set_tempo Set the project tempo in BPM (downstream: seconds_per_beat = 60 / bpm). Write set_time_signature set_time_signature Write set_track_volume_pan Set fader/pan. Accepts fuzzy values ('-6dB', '+3', '50%', 'L50', 'center'). Write suggest_chord_progression A genre-typical diatonic progression as Roman numerals + concrete MIDI. Write transpose_notes Transpose a take's notes — the APPLY verb for key/mode retargeting.

READ 14 tools

Read analyze_audio_character Render stems/master to WAV and compute the post-FX sonic fingerprint: Read analyze_groove Compute swing%% and tightness from raw MIDI PPQ onset deviation off the grid. Read analyze_harmony analyze_harmony Read get_connection_status get_connection_status Read get_fx_params Decode an FX chain's parameters BY NAME (e.g. compressor ratio), not as opaque 0–1. Read get_genre_profile A style's typical progressions / scales / BPM range / instruments / drum rhythms. Read get_project_info Tempo, time signature, length, track count, and transport state. Read get_scale_notes MIDI notes for a key/mode so generated notes stay diatonic. Read get_track_midi Read a take's MIDI notes (pitch, start/duration in BEATS, velocity) + CC. Read list_installed_fx Parse REAPER's plugin cache .ini files so recommendations only suggest owned plugins. Read list_style_fingerprints List cached target fingerprints (e.g. 'classical', 'hiphop', 'dominic-fike-sunburn'). Read list_tracks The typed track tree: name, vol/pan, mute/solo, role, FX-chain names, item count. Read resolve_time Parse '8 bars' / '1:30' / keywords into concrete tempo-aware positions. Read resolve_track Fuzzy-match a track by name/role, with disambiguation ('2 drum tracks: which?').

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Orpheus

How do I prevent bulk modifications through Orpheus? +

The Orpheus server has 18 write tools including add_fx_by_name, apply_mix_balance, constrain_to_key. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Orpheus.

How many tools does the Orpheus MCP server expose? +

39 tools across 3 categories: Execute, Read, Write. 14 are read-only. 25 can modify, create, or delete data.

How do I enforce a policy on Orpheus? +

Register the Orpheus MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Orpheus tool call.

Deterministic rules across all 39 Orpheus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ORPHEUS →

Instant setup, no code required.

39 Orpheus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.