Skip to main content
Glama

AI Producer Hub

Fleet orchestration MCP server for the audio production stack. Generates songs via SongGeneration LeVo, loads them to VirtualDJ decks, produces multi-track albums, and sets up live streaming.

Quick Start

git clone https://github.com/sandraschi/ai-producer-hub
cd ai-producer-hub
uv sync
uv run -m ai_producer_hub    # MCP server (MIDI tools)

Webapp: cd webapp && npm install && npx vite --port 10707

Related MCP server: FL Studio MCP Server

Tools

Tool

What it does

songgen_to_deck(lyrics, genre, tempo, deck_id)

Generate song via LeVo → load to VDJ deck

ai_dj_set(theme, num_tracks, bpm)

Generate multi-track DJ set across decks

album_factory(theme, num_tracks)

Multi-track album, optionally to Plex

live_stream_producer(theme, duration)

Set up streaming with AI-generated music

ai_mashup(track_a, track_b)

Mashup plan from VDJ library search

hub_status()

Check all fleet server health

list_midi_devices()

Enumerate MIDI hardware

record_midi_performance(device, duration)

Record MIDI to file

Architecture

AI Producer Hub (MCP stdio)
  ├──→ songgeneration-mcp (HTTP :10885) — LeVo AI generation
  ├──→ virtualdj-mcp (HTTP :10877) — DJ decks, stems, mixing
  ├──→ reaper-mcp (HTTP :10797) — DAW mastering
  └──→ obs-mcp (HTTP :10819) — Live streaming

Sub-servers can run on any reachable host. Configure via SONGGEN_BASE, VDJ_BASE, REAPER_BASE, OBS_BASE env vars.

Requirements

  • Python 3.11+

  • Running sub-servers (songgeneration-mcp, virtualdj-mcp) for orchestration tools

  • python-rtmidi + mido for MIDI tools

Available Tools

22 tools
ai_analyze_productionC

AI-powered analysis of production progress and quality.

Inputs: production_id (required), analysis_type. Returns: object

ai_colaborate_workflowC

Conversational tool returns for natural AI collaboration.

This enables ongoing conversations about production workflows with context awareness and natural language responses.

Inputs: user_input (required), conversation_history. Returns: object

ai_dj_setB

Generate a complete AI DJ set from a theme.

This workflow:

  1. Generates multiple tracks based on theme variations

  2. Analyzes BPM and key of each

  3. Orders tracks for harmonic mixing

  4. Loads to VirtualDJ decks

  5. Configures automix

  6. Optionally starts recording

Inputs: theme (required), bpm_range, num_tracks, duration_minutes. Returns: object

ai_mashupA

Create an AI-powered mashup of two tracks.

Workflow:

  1. Find tracks in Plex library

  2. Extract stems from both

  3. Analyze compatible elements

  4. Generate mashup arrangement

  5. Load to VirtualDJ for preview

Inputs: track_a_search (required), track_b_search (required), mashup_style. Returns: object

ai_orchestrate_productionC

SEP-1577 Sampling Implementation: AI autonomously decides tool usage and sequencing.

This demonstrates the core sampling capability where the LLM can autonomously orchestrate complex workflows without client round-trips.

Inputs: available_tools (required), workflow_description (required). Returns: object

ai_produce_trackC

AI-driven complete track production with sampling capabilities.

This tool demonstrates SEP-1577 by autonomously orchestrating the entire music production pipeline using sampling with tools.

Inputs: theme (required), bpm, genre, complexity, +3 more. Returns: object

ai_stream_productionC

Autonomous live streaming production with AI-generated content.

Inputs: theme (required), platform, duration_hours. Returns: object

album_factoryA

Generate a complete album from a theme.

This workflow:

  1. Creates track list with variations on theme

  2. Generates all tracks via Suno

  3. Masters each track

  4. Creates album metadata

  5. Saves to Plex library

Inputs: album_theme (required), num_tracks, album_title, save_to_plex. Returns: object

bpm_bridge_generatorA

Generate a transition track that bridges between two BPMs.

Perfect for smooth genre transitions in a DJ set. Generates a track that starts at one BPM and gradually transitions to another.

Inputs: target_bpm (required), current_bpm (required), style. Returns: object

hub_statusB

Get status of all mounted servers and available workflows.

Inputs: no named parameters. Returns: object

karaoke_generatorA

Generate a karaoke track from lyrics.

Workflow:

  1. Send lyrics to Suno with style

  2. Generate full song

  3. Load to VirtualDJ

  4. Enable karaoke mode (removes vocals, shows lyrics)

Inputs: lyrics (required), style, deck_id. Returns: object

list_midi_devicesA

List all available MIDI input and output devices.

Scans the system for connected MIDI devices including:

  • USB MIDI keyboards

  • Hardware synthesizers

  • Virtual MIDI ports (loopMIDI, IAC, etc.)

  • DAW MIDI interfaces

Returns: Dict with lists of input and output devices

Example output: { "inputs": ["MPK mini 3", "loopMIDI Port"], "outputs": ["Microsoft GS Wavetable Synth", "loopMIDI Port"] }

Inputs: no named parameters. Returns: object

live_stream_producerB

Run a live streaming DJ set with AI-generated music.

The ultimate AI producer workflow:

  1. Start OBS streaming

  2. Generate initial tracks

  3. Start VirtualDJ mixing

  4. Continuously generate new tracks

  5. Hot-swap new tracks into the mix

  6. Run for specified duration

Inputs: theme (required), platform, duration_hours, generate_interval_minutes. Returns: object

midi_monitorA

Monitor MIDI input and display incoming messages.

Useful for:

  • Testing MIDI connections

  • Learning what messages your device sends

  • Debugging MIDI setups

Inputs: device_index, duration_seconds. Returns: object

midi_to_ai_seedA

Use a MIDI recording as a seed for AI music generation.

Takes your played melody/chords and:

  1. Analyzes the musical content

  2. Extracts key, tempo, chord progression

  3. Creates a prompt for AI expansion

  4. Generates full track based on your input

Inputs: midi_file (required), expansion_style, target_duration. Returns: object

midi_to_reaperB

Import a MIDI file into Reaper DAW.

Sends the MIDI file to Reaper for:

  • Audio rendering with virtual instruments

  • Further editing and arrangement

  • Mixing and mastering

Inputs: midi_file (required), track_name. Returns: object

play_midi_fileC

Play a MIDI file through an output device.

Sends the MIDI file to your synthesizer/sound module for real-time playback.

Inputs: midi_file (required), device_index. Returns: object

producer_helpB

Get help for AI Producer Hub workflows.

Inputs: topic. Returns: result

record_midi_performanceB

Record a MIDI performance from an input device.

Captures all MIDI events (notes, control changes, pitch bend) from the specified device for the given duration.

Inputs: output_file, device_index, duration_seconds. Returns: object

remix_plex_trackA

Take a track from Plex library and create an AI remix.

Workflow:

  1. Search Plex for the track

  2. Extract stems (vocals, instruments, bass, drums)

  3. Send stems + style to Suno for reimagining

  4. Generate new remix

  5. Load to VirtualDJ deck

Inputs: plex_search (required), remix_style (required), deck_id. Returns: object

send_midi_noteC

Send a MIDI note to an output device.

Inputs: note (required), device_index (required), channel, velocity, +1 more. Returns: object

songgen_to_deckB

Generate an AI track using LeVo model and load it to VirtualDJ.

This is the core AI Producer workflow with state-of-the-art AI:

  1. Send lyrics and parameters to SongGeneration LeVo model

  2. Generate high-quality vocals + professional backing tracks

  3. Optional stem separation (vocals/instruments)

  4. Download the generated audio

  5. Load to VirtualDJ deck

  6. Ready to mix!

Inputs: lyrics (required), mood, genre, tempo, +3 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 22 tools

    Disambiguation3/5

    The MIDI tools (record_midi_performance, send_midi_note, play_midi_file, midi_monitor, list_midi_devices) are clearly distinct, but the AI workflow tools overlap heavily: ai_produce_track, ai_orchestrate_production, and ai_colaborate_workflow all describe autonomous AI orchestration, and live_stream_producer vs ai_stream_production appear to do nearly the same thing. Descriptions help somewhat but boundaries between the AI-orchestration tools are genuinely fuzzy.

    Naming Consistency4/5

    All names use snake_case, which is consistent, and many follow a verb_noun pattern (send_midi_note, play_midi_file, list_midi_devices). There are deviations (ai_* prefixed tools, noun-style album_factory/karaoke_generator/hub_status) and a typo (ai_colaborate_workflow), but the surface remains readable and predictable.

    Tool Count3/5

    At 22 tools this sits in the heavy range for a server whose purpose is one production pipeline, and several tools (multiple AI-orchestration and streaming variants) feel redundant rather than each earning its place. It is not extreme, but it leans toward over-provisioned.

    Completeness4/5

    The domain (AI music production and DJ mixing) is covered broadly: MIDI I/O, track/album generation, remix, mashup, karaoke, streaming, and library integration. Minor gaps exist around explicit track editing/mixing controls, but core lifecycle workflows are represented.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers