io. github. erliona/ tunova
by erliona · remote · no sign-in to list tools · v0.1.1 · published by GitHub user erliona
Generate Suno AI music (v5.5) from any MCP client. Async; billed only on success.
3 tools: 1 change things and 2 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads2Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http tunova https://api.tunova.ai/mcp --header 'X-API-Key: <your-x-api-key>'Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
3 tools
Changes things 1Claude Code: ask
generate_songStart generating a song with Suno.No findings
Why it is in this group
- The name "generate_song" says "generate": a word for a change.
Description, as the server wrote it Start generating a song with Suno. Returns immediately with a job_id — a full render takes 1-3 minutes, so this does NOT return audio. After calling this, call wait_for_song with the returned job_id to get the audio URL when ready. Costs 10 tokens, billed only on success.
Only reads 2Claude Code: allow
check_songGet the current status of a song job by job_id — a single check with no waiting.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get the current status of a song job by job_id — a single check with no waiting. Returns the audio URLs if complete, an error if it failed, or 'processing' if still rendering.
wait_for_songWait for a song job to finish and return the audio when ready.No findings
Why it is in this group
- The name "wait_for_song" says "wait": a word for reading.
Description, as the server wrote it Wait for a song job to finish and return the audio when ready. Polls server-side for up to ~45 seconds. If the song is ready, returns the clips with audio URLs. If it is still rendering, returns its status so you can call wait_for_song again with the same job_id. Safe to call repeatedly — it only reads status, never starts a new song.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Oct 22, 2026, 14:58 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- https://api.tunova.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.tunova.ai/mcp: tools/list returned 3 tools to an anonymous client, including generate_song (write)
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http tunova https://api.tunova.ai/mcp --header 'X-API-Key: <your-x-api-key>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__tunova__wait_for_song",
"mcp__tunova__check_song"
],
"ask": [
"mcp__tunova__generate_song"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as tunova. Review it before you use it.
