ismailBLOCK
A DAW for AI agents: write music as text, read the audio back as text. MCP server, CLI and an agent skill.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
New here? You don't need to know music or code. Open an AI agent that can run programs on your computer (Claude Code, Codex, Cursor, or the Code tab in the Claude desktop app) and paste this line: `` Set me up with ismail: https://github.com/newsbubbles/ismail `` It installs everything, asks what you want to make, and plays you a first idea. If you have a VR headset, it can put you on a stage inside your music later. You don't need to know what a "skill", "MCP" or "plugin" is: your agent handles that.A DAW for AI agents. It can't hear, so it reads. And it plays live.
Your agent writes the song as notes, sounds and code, reads back what it made, and then performs it: DJ decks, transitions, requests taken while the music plays. Away from the desk, the set goes in your pocket: a phone page you listen to with the screen off and talk back to through your earbuds.
[](https://github.com/newsbubbles/ismail/actions/workflows/tests.yml)
[](https://newsbubbles.github.io/ismail/)
Agents: start at AGENTS.md.
[Listen to songs an agent made with it](https://newsbubbles.github.io/ismail/), each shown with the text the agent read while making it. The playhead runs across that text as the song plays.
82fc80bfc502OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ismail -- uvx ismail==0.3.0 mcp
Trust audit
BLOCKgrade F · trust 40/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (16 observation(s))
- Shell
- declared (8 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
exec(p['code'], ns)
exec(compile(open(_pass, encoding='utf-8').read(), _pass, 'exec'),
if (ASIDE.has(c.type)) exec(c);
else await exec(c);
<!doctype html>
ack_0.wav
ack_1.wav
ack_2.wav
ack_3.wav
ack_4.wav
return getattr(importlib.import_module(f'ismail.voices.{cat}.{voice}'), 'INFO', None)return importlib.import_module(f"{__name__}.{rel}")return importlib.import_module(self.real)
function flushEv(beacon) {if (beacon && navigator.sendBeacon) { navigator.sendBeacon('api/events', new Blob([body], { type: 'application/json' })); return; }with urllib.request.urlopen(f'http://127.0.0.1:{port}/health', timeout=2) as r:return f'http://127.0.0.1:{port}/eye/'req = urllib.request.Request(f"http://127.0.0.1:{port}/", data=json.dumps({'op': name, 'args': args}).encode(),return (f"stream {name}: http://127.0.0.1:{port}{r['path']} | {r['format']} {r['channels']} ch {r['rate']} Hz | "req = urllib.request.Request(f'http://127.0.0.1:{port}/agent', headers={'Content-Type': 'application/json'},return hashlib.sha1(blob.encode()).hexdigest()[:20]
return hashlib.sha1(s.encode('utf8')).hexdigest()[:12]key = hashlib.sha1(f'{src}|{st.st_size}|{st.st_mtime_ns}'.encode('utf8')).hexdigest()[:16]h = hashlib.sha1()
return hashlib.sha1(blob.encode()).hexdigest()[:20]
Gates applied: no_behavioural_pass.
82fc80bfc502full audit observations/trust-audit/mcp-server/newsbubbles__ismail.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 82fc80bfc502 | BLOCK | F | 40 | first audit |
Questions
What is the ismail MCP server?
A DAW for AI agents: write music as text, read the audio back as text. MCP server, CLI and an agent skill.
Is ismail safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (40/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does ismail need?
It reads VR_PASS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does ismail run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as ismail.
How current is this page?
The grade is for one exact copy of the source (82fc80bfc502), read on 2026-10-10. The repository is watched and re-audited when it changes.