Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PerIPan/music-workflow-skills --skill ableton-mcpgit clone --depth 1 https://github.com/PerIPan/music-workflow-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/peripan/music-workflow-skills/ableton-mcp)<a href="https://agentmods.dev/skills/peripan/music-workflow-skills/ableton-mcp"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/ableton-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/peripan/music-workflow-skills/ableton-mcp"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/ableton-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.03454 |
| Opus 5.5 | $0.00022 | $0.01382 |
| Sonnet 5.5 | $0.00011 | $0.00691 |
| Haiku 4.5 | $0.00006 | $0.00345 |
Grade A, and why
ableton-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ableton Live via MCP
Claude drives a live Ableton Set through the AbletonMCP server (jpoindexter fork v2.0.0,
128 tools, all prefixed mcp__ableton__). Limits below are for this fork.
References (read on demand):
references/setup-install.md— first-time install (Remote Script + server + verify)references/troubleshooting.md— connection failures, tool errorsreferences/als-xml.md— reading Arrangement content from the saved.als(MCP can't)
For arrangement craft (section design, bass/drum patterns, FX chains) use the
ableton-arrangement skill; this skill is the mechanics and the gotchas.
Mental model
- Live and stateful. Every call mutates the open Set immediately. No preview/dry-run. Undo is Live's own Cmd/Ctrl-Z.
- Single session. Controls one Ableton instance — the frontmost open Set. No diffing two Sets, no background operation. Two clients on one Live collide; work sequentially.
- No autosave. Claude can't save/open/new a Set — the USER Cmd-S's. After a Set switch, the server re-attaches to the new frontmost Set.
- Deferred tools (Claude Code). Load schemas before first use:
ToolSearch select:mcp__ableton__<name>. - Reason in BARS, never seconds. Sizes and positions are bar counts; convert everything to bars up front.
Tool map
| Area | Representative tools |
|---|---|
| Transport | start/stop_playback, start/stop_recording, set_tempo, set_metronome, jump_to_time, capture_midi |
| Tracks | create_midi/audio/group_track, set_track_name/volume/pan/mute/solo/arm/color, set_track_input/output_routing, delete/duplicate_track, freeze/flatten |
| Clips | create/delete/duplicate/fire/stop_clip, set_clip_name/color/loop/gain/pitch, get_clip_notes |
| MIDI notes | add_notes_to_clip, remove_notes (range), remove_all_notes, transpose_notes, quantize_clip_notes, humanize_clip_timing/velocity |
| Devices / FX | search_browser, load_instrument_or_effect, get/set_device_parameter, toggle/delete_device, move_device_left/right, get_rack_chains |
| Scenes | create/delete/duplicate/fire_scene, set_scene_name/color, get_all_scenes |
| Mixing | set_send_level, get/set_return_volume/pan, set_master_volume/pan |
| Automation | get/set/clear_clip_automation, toggle_session_record, set_overdub |
| AI helpers | get_scale_notes, generate_drum_pattern, generate_bassline |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +80 lines · -17 tokens per session 42ec85b68b31
- 2mo ago First seen · 137 lines · 72 tokens per session scan A c3b040d8fc99
ableton-mcp is a skill published in the GitHub repository PerIPan/music-workflow-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 3,454 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
ableton-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ableton-mcpPerIPan/music-workflow-skills | Skill | 3 | 1mo ago | MIT | A | 55 | Claude Code, Codex |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |
| accessibility-patternsvibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 24 | Claude Code, Codex |
| design-reviewjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 108 | Claude Code |
| react-patternsjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 110 | Claude Code |