Livepilot MCP server

Read from the package source without running it. The installed server may list more.

• add_session_memory

  Add an ephemeral session memory entry (observation, hypothesis, decision, issue).

• analyze_mix

  Build full mix state and run all critics.

• analyze_phrase_arc

  Analyze a captured audio phrase for musical quality.

• analyze_reference_gaps

  Analyze gaps between your project and a reference.

• analyze_sample

  Analyze a sample and build a complete SampleProfile.

• analyze_sound_design

  Build full sound design state and run all critics for a track.

• apply_creative_constraint_set

  Apply creative constraints to focus suggestions.

• apply_semantic_move

  Compile and optionally execute a semantic move against the current session.

• atlas_chain_suggest

  Suggest a full device chain for a track role.

• atlas_compare

  Compare two devices — strengths, weaknesses, and recommendation for a role.

• atlas_device_info

  Get complete atlas knowledge about a device — parameters, recipes, pairings, gotchas.

• atlas_search

  Search the device atlas for instruments, effects, kits, or plugins.

• atlas_suggest

  Suggest devices for a production intent.

• augment_with_samples

  Plan sample-based layers to add to the existing session.

• build_project_brain

  Build a full Project Brain snapshot from the current Ableton session.

• build_reference_profile

  Build a reference profile from an audio file or style/genre name.

• build_song_brain

  Build the musical identity model for the current song.

• check_safety

  Validate a proposed action against safety policies before executing.

• commit_experiment

  Commit the winning branch — re-apply its moves permanently.

• commit_preview_variant

  Commit the chosen variant from a preview set — APPLIES the plan.

• compare_experiments

  Compare and rank all evaluated branches in an experiment.

• compare_phrase_impact

  Compare phrase-level emotional impact across multiple sections.

• compare_phrase_renders

  Compare multiple audio captures and rank by musical quality.

• compare_preview_variants

  Compare and rank variants in a preview set.

• compose

  Plan a full multi-layer composition from a text prompt.

• create_experimentwrite action

  Create an experiment set to compare multiple approaches.

• create_preview_setwrite action

  Create a preview set with multiple creative options.

• detect_hook_neglect

  Detect if a strong hook exists but is underused across sections.

• detect_identity_drift

  Detect whether recent changes have damaged the song's identity.

• detect_payoff_failure

  Detect where the song should deliver a payoff but doesn't.

• detect_repetition_fatigue

  Detect repetition fatigue — are patterns overused?

• detect_role_conflicts

  Detect role conflicts — are tracks fighting for the same musical space?

• detect_stuckness

  Detect whether the session is losing momentum.

• develop_hook

  Suggest development strategies for a hook.

• discard_experiment

  Discard an entire experiment — no changes are kept.

• discard_preview_set

  Discard an entire preview set and all its variants.

• distill_reference_principles

  Learn musical principles from a reference — not surface traits.

• evaluate_mix_move

  Score a mix change using the evaluation fabric.

• evaluate_sample_fitwrite action

  Run the 6-critic battery to evaluate how well a sample fits the current song.

• evaluate_with_fabric

  Evaluate a move using the unified Evaluation Fabric.

• explain_preference_vs_identity

  Explain how taste preference and song identity score a candidate.

• explain_song_identity

  Explain the current song's identity in human musical language.

• explain_taste_inference

  Explain why the system thinks the user prefers certain approaches.

• find_primary_hook

  Find the most salient hook in the current session.

• generate_constrained_variants

  Generate creative variants under active constraints.

• generate_m4l_effect

  Generate a Max for Live device from gen~ codebox code.

• generate_reference_inspired_variants

  Generate creative variants inspired by a distilled reference.

• get_action_ledger_summary

  Return a summary of recent semantic moves from the action ledger.

• get_anti_preferences

  Return all recorded anti-preferences — dimensions the user has repeatedly disliked.

• get_capability_state

  Probe the runtime and return a capability state snapshot.

• get_composition_plan

  Preview what compose would do without executing or spending credits.

• get_last_move

  Return the most recent semantic move from the action ledger.

• get_masking_report

  Get detailed frequency collision report.

• get_mix_issueswrite action

  Run all mix critics and return detected issues only.

• get_mix_summary

  Lightweight mix overview — track count, issue count, dynamics state.

• get_patch_modelwrite action

  Get the structural patch model for a track's device chain.

• get_performance_safe_moves

  Get available safe moves for live performance.

• get_performance_state

  Get current live performance overview — scenes, energy, safe moves.

• get_project_brain_summary

  Get a lightweight Project Brain summary — track count, section count, stale status.

• get_promotion_candidates

  Check the session ledger for entries eligible for memory promotion.

• get_sample_opportunities

  Analyze current song and identify where samples could improve it.

• get_session_kernel

  Build the unified turn snapshot for V2 orchestration.

• get_session_memory

  Return recent session memory entries — ephemeral observations, hypotheses, decisions.

• get_session_story

  Get the narrative of the current session.

• get_sound_design_issueswrite action

  Run all sound design critics and return detected issues only.

• get_taste_dimensions

  Return all taste dimensions — user preferences inferred from kept/undone outcomes.

• get_taste_graph

  Get the full TasteGraph — extended preferences including move families, device affinities, novelty tolerance, and dimension weights.

• infer_section_purposes

  Infer what each section/scene is trying to do musically.

• install_m4l_device

  Copy a .amxd file to Ableton's User Library.

• list_genexpr_templates

  List available gen~ DSP building block templates.

• list_open_creative_threads

  List all open (non-stale) creative threads in the session.

• list_semantic_moves

  List available semantic moves — high-level musical intents.

• map_reference_principles_to_song

  Map distilled reference principles to the current song.

• measure_hook_salience

  Measure the salience of a specific hook or the primary hook.

• open_creative_thread

  Open a new creative thread — an unresolved creative goal.

• plan_mix_move

  Get ranked move suggestions based on current mix issues.

• plan_reference_moves

  Plan concrete moves to close reference gaps.

• plan_sample_workflow

  Full end-to-end sample workflow: analyze, critique, select technique, compile plan.

• plan_scene_handoff

  Plan a safe transition between two scenes.

• plan_slice_workflow

  Plan an end-to-end slice workflow for a sample.

• plan_sound_design_move

  Get ranked move suggestions based on current sound design issues.

• preview_semantic_move

  Preview what a semantic move will do before applying it.

• propose_next_best_move

  Propose the best semantic moves for a natural language request.

• rank_by_taste_and_identity

  Rank candidates with separated taste and identity scoring.

• rank_hook_candidates

  List and rank all hook candidates in the session.

• rank_moves_by_taste

  Rank semantic moves by taste fit for the current user.

• record_anti_preference

  Record a user dislike for a dimension+direction. direction must be 'increase' or 'decrease'.

• record_positive_preference

  Record a user preference for more/less of a dimension.

• record_turn_resolution

  Record what happened in a creative turn.

• render_preview_variant

  Render a short preview of a specific variant for evaluation.

• resume_last_intent

  Resume the most recent unresolved creative intent.

• run_experimentwrite action

  Run all pending branches in an experiment.

• scan_full_library

  Scan the full Ableton browser and rebuild the device atlas.

• score_emotional_arc

  Score the emotional arc of the arrangement.

• score_phrase_impact

  Score a section's emotional impact as a musical phrase.

• search_samples

  Search for samples across Splice library, Ableton browser, and local filesystem.

• start_rescue_workflow

  Start a structured rescue workflow for a specific stuckness type.

• suggest_momentum_rescue

  Suggest strategic moves to restore session momentum.

• suggest_payoff_repair

  Generate repair strategies for detected payoff failures.

• suggest_sample_technique

  Suggest sample manipulation techniques from the technique library.

• Code scan302 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 4 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

92/100

higher than 95% of 48,255 servers

Tools

100

the typical server has 7

Tools that change things

7%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

74

more than 95% of 28,688 servers

Livepilot: common questions

Is Livepilot MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the Livepilot safety report

How do I install Livepilot?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Livepilot need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Livepilot maintained?

The last commit was 41 days ago (2026-09-24). The latest release is v1.10.4.

How does Livepilot compare with other MCP servers?

safety score 92/100 (higher than 95% of 48,255 servers); tools 100 (the typical server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.