What is ableton-mcp CLAUDE.md?

Project instructions for ableton-mcp, an MCP server that lets an AI tool control Ableton Live, music production software. They describe its Python and TypeScript parts, how they communicate, and the commands used to test, type-check, and build them.

Use them when developing, testing, type-checking, or packaging ableton-mcp, including its remote script and TypeScript MCP server.

They keep changes compatible with Ableton Live's embedded Python and its main-thread-only API, while making sure both server processes remain testable.

How sketchymeow/ableton-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sketchymeow/ableton-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.

Copy the file

curl -O https://raw.githubusercontent.com/sketchymeow/ableton-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sketchymeow/ableton-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sketchymeow/ableton-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sketchymeow/ableton-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sketchymeow/ableton-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sketchymeow/ableton-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sketchymeow/ableton-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sketchymeow/ableton-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 902 This file is loaded in full into every session.

When invoked 902 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00902	$0.00902
Opus 5	$0.00451	$0.00451
Sonnet 5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 9d ago against content hash 2972120d4ce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ableton-mcp CLAUDE.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 9d 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ableton-mcp

MCP server that controls Ableton Live. Two processes: a Python remote script inside Live and a TypeScript MCP server, talking over TCP on 127.0.0.1:9877 with 4-byte length-prefixed JSON frames.

Commands

uv sync && uv run pytest — remote script tests, no Live needed (fake LOM in tests/unit/fake_live.py). Always uv, never pip.
cd server && npm install && npm test — MCP server tests (vitest)
cd server && npx tsc --noEmit — typecheck
cd server && npm run build — esbuild bundle to server/dist/index.js (includes a stdio initialize smoke test)
cd server && npm run build:mcpb — Claude Desktop bundle (node-type, packed with the official mcpb CLI)

Architecture rules

remote_script/AbletonMCP/ runs inside Live's embedded Python:
- Python 3.7-safe syntax only (Live 11 floor), stdlib only, no third-party deps. All the real logic lives here.
- No threads. BridgeServer.tick() is pumped from Live's main thread every ~100ms via schedule_message(1, ...). The Live API is main-thread only; the tick model makes that hold by construction.
- __init__.py must stay importable outside Live: anything touching Live or ableton.v2 imports lazily (see surface.py, handlers).
server/ is the MCP server: TypeScript, @modelcontextprotocol/server v2 (McpServer, serveStdio, zod v4 schemas). Tools are thin wrappers; trivial one-property reads/writes go through the generic bridge commands (get_property/set_property/call_method); the bridge only gains commands for compound reads, batched writes, or logic that needs Live-side context.
server/src/protocol.ts must stay wire-compatible with remote_script/AbletonMCP/core/protocol.py. Both have framing tests.
One command registry dict in the remote script. Never maintain parallel command lists.
Socket binds 127.0.0.1 only. Keep it that way.
MCP clients stringify numbers on union-typed fields; the bridge coerces numeric strings everywhere a float is expected. Don't remove that.
Object-valued LOM properties (routing, selected_) can't take scalars: set_property resolves against the available_ sibling list, or takes a value_path. Live float properties reject ints and strings (Boost.Python TypeError) — set_with_float_retry handles it.

Read the full file on GitHub · 69 lines

Changes

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.

9d ago First seen · 69 lines · 902 tokens per session scan A 2972120d4ce3

Subscribe to this mod's changes

ableton-mcp CLAUDE.md is an instructions file published in the GitHub repository sketchymeow/ableton-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 902 tokens to every session, about $0.0045 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 2026-08-31.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

ableton-mcp: Instructions file for Claude Code