Borrowing it
Nothing to install: this file belongs to bschoepke/ableton-live-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bschoepke/ableton-live-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/bschoepke/ableton-live-mcpWrote 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/instructions/bschoepke/ableton-live-mcp/agents-md)<a href="https://agentmods.dev/instructions/bschoepke/ableton-live-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bschoepke/ableton-live-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.12257 | $0.12257 |
| Opus 5 | $0.06129 | $0.06129 |
| Sonnet 5 | $0.02451 | $0.02451 |
| Haiku 4.5 | $0.01226 | $0.01226 |
Grade A, and why
ableton-live-mcp AGENTS.md 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Ableton-Live-MCP-ULTRA-v2 AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ableton Live MCP Setup
MCP initialize instructions are intentionally compact; when they point to AGENTS.md, use this file for repo-specific Ableton, Max for Live, reliability, validation, and recovery guidance.
-
From this repository checkout, install the package into the agent environment:
python -m pip install -e ".[dev]"The
devextra intentionally includes the Ableton-only visual capture dependencies used for M4L UI verification. For a lean runtime install that still needs screenshots, install thevisualextra too. -
Install the Ableton Remote Script:
ableton-live-mcp-install-remote-script -
Start Ableton Live, open Settings, and select
Ableton_Live_MCPas a Control Surface. -
Register the MCP server in your MCP client:
{ "mcpServers": { "ableton": { "command": "ableton-live-mcp" } } } -
Validate the connection while Ableton is running:
ableton-live-mcp-validateFor a deliberate quick health probe against a stressed or possibly wedged set, use a bounded strict check such as:
ableton-live-mcp-validate --timeout 3 --strict-timeout --allow-stale-remote-script
The Remote Script binds only to 127.0.0.1. If Ableton was already open when the script was installed, restart Ableton or reload the Control Surface.
After changing files under Ableton_Live_MCP/, reinstall the Remote Script and reload the Control Surface before treating Live validation as current. The running Control Surface does not pick up repository edits automatically; stale installed scripts can make bridge behavior, timeout handling, or generated-device triggers look broken after the source has been fixed. ableton-live-mcp-validate checks the installed Remote Script files plus the running live_ping runtime version, loaded-code fingerprint, and script hash; do not ignore a stale/missing runtime marker, code fingerprint, or hash unless deliberately validating old code.
Reloading the Control Surface or restarting Live can interrupt playback and the user's current set. Ask for explicit user authorization before doing either, then rerun ableton-live-mcp-validate and require runtime_current: true and live_mutations_safe: true before claiming current-runtime e2e validation or sending generated-device mutations.
If a known MCP tool appears in the active client with an obviously stale or no-argument schema, such as live_agent_audio_tap rejecting {"command": "stop"} or live_transport rejecting {"action": "play"}, stop using that client schema. Run ableton-live-mcp-validate and reload/restart the MCP server or MCP client session so tools/list is refreshed; do not keep trying calls that the active schema cannot represent.
Save, crash-report, and "Recover last Live Set" dialogs are common after forced recovery. Treat any Live modal as a hard blocker for MCP mutations: inspect the Ableton Live UI, resolve only the Ableton dialog, then rerun validation before continuing. If the user has authorized a fresh disposable validation set and the open set contains only generated test material, choose the non-saving/non-recovery path such as "Don't Save" or "No"; if user work might be present, stop and ask before dismissing it.
If validation fails with live_error, preserve live_failure_type, runtime_mismatch, and runtime_next_action in the investigation notes. live_main_thread_timeout often means a modal dialog or heavy UI/indexing work is blocking Live; inspect the UI before sending more mutations. bridge_not_listening means the Control Surface bridge is not accepting localhost connections. Installed files may still be current in either case, so do not infer current-runtime behavior from source tests alone.
When the bridge socket still responds but Live's main thread does not execute scheduled work, validation reports live_failure_type: "live_main_thread_hung" and may include bridge_status.server_thread_responsive: true. Treat this as a real Live hang, not a retryable command failure: stop sending Live API mutations, avoid piling up queued callbacks, and ask for explicit authorization before reloading the Control Surface or restarting Live. Use live_bridge_status only for no-Live-API socket-thread diagnostics while the set is wedged.
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.
- 8d ago First seen · 311 lines · 12,257 tokens per session scan A 529f58834655
ableton-live-mcp AGENTS.md is an instructions file published in the GitHub repository bschoepke/ableton-live-mcp (215 stars, last pushed 1mo ago), licensed MIT. It adds 12,257 tokens to every session, about $0.0613 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.