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.
git clone --depth 1 https://github.com/farmhutsoftwareteam/ableton-mcp-extendedWrote 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/mcp/farmhutsoftwareteam/ableton-mcp-extended/ableton-mcp-suite)<a href="https://agentmods.dev/mcp/farmhutsoftwareteam/ableton-mcp-extended/ableton-mcp-suite"><img src="https://agentmods.dev/badge/mcp/farmhutsoftwareteam/ableton-mcp-extended/ableton-mcp-suite/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/mcp/farmhutsoftwareteam/ableton-mcp-extended/ableton-mcp-suite"><img src="https://agentmods.dev/badge/mcp/farmhutsoftwareteam/ableton-mcp-extended/ableton-mcp-suite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ableton-mcp-suite 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.
What it actually says
{ "ableton-mcp-suite": { "command": "uvx", "args": [ "ableton-mcp-suite" ] } }
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 First seen · 8 lines scan A 384719f5a04c
ableton-mcp-suite is an MCP server published in the GitHub repository farmhutsoftwareteam/ableton-mcp-extended (0 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other mcp servers, from other repositories
ableton-live-mcp
Control Ableton Live 11/12 with 156 typed MCP tools for MIDI, devices, arrangement, mixing, automation, and offline .als analysis. Runs locally from the mcp-server-ableton-live Python package.
ableton-mcp-server
MCP server "ableton-mcp-server" as configured in ntworm/ableton-mcp-server. Launched with https://github.com/ntworm/ableton-mcp-server/releases/download/v0.7.0/ableton-mc.
livepilot
Agentic production system for Ableton Live 12 — 474 tools, 57 domains, 44 semantic moves. Device atlas (5264 devices, 120 enriched, 7 indexes), Splice intelligence (gRPC + GraphQL describe-a-sound + preview + collections + presets), 9-band spectral percep. Runs locally from the livepilot npm package.
ableton-control-deck
MCP server "ableton-control-deck" as configured in remymazmanian/ableton-control-deck. Runs locally from the ableton-control-deck npm package.
ableton-auto-mix-mcp
MusicMixCode — MCP server for AI-driven auto-mixing and mastering in Ableton Live: style-based mixing, preview renders, release checks. Runs locally from the ableton-auto-mix-mcp Python package.
ableton-mind
Control Ableton Live from Claude, Cursor or Codex with LOM tools, device knowledge and recipes. Runs locally from the ableton-mind npm package.