ableton-mcp@0.5.0
CAUTION· static onlyPublisher claims: "Enables MCP clients such as Claude Code to control Ableton Live 12.1+ through a stdlib-only Remote Script, covering tracks, Drum Rack kits, MIDI clips, playback, and undo, with offline .mid export when Live is closed." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- ableton.com (its own)
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-09 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
vital.read_preset("/etc/passwd", tmp_path)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **Max for Live Developer Mode** (12.4) adds "Copy Max for Live Path" on UI elements ([Ableton KB](https://help.ableton.com/hc/en-us/articles/29426709984796)). Suite only in practice.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.return FAIL, f"{conn_file} has mode {mode:o}, expected 600", f"chmod 600 '{conn_file}'"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- [Max for Live Developer Mode](https://help.ableton.com/hc/en-us/articles/29426709984796)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert status == doctor.FAIL and "chmod 600" in fixFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- **Max for Live Developer Mode** (12.4) adds "Copy Max for Live Path" on UI elements ([Ableton KB](https://help.ableton.com/hc/en-us/articles/29426709984796)). Suite only in practice.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert b"\xff\x51\x03\x07\xa1\x20" in data # 500000 us/quarter = 120 BPMFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.if subprocess.run(["pgrep", "-x", "Vital"], capture_output=True).returncode == 0: # 0: a process matchedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- [Max for Live Developer Mode](https://help.ableton.com/hc/en-us/articles/29426709984796)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen([str(VITAL_BINARY), str(path)], start_new_session=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim ok2ju: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Hex-encoded string detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.