Koskamo

Tunova MCP

An MCP server that enables AI agents to generate music using Suno AI models v6 and v5.5. It provides tools to generate songs from prompts, check song status, and wait for completion. The service operates on a prepaid token basis where users pay only for successful renders, with automatic refunds for failures.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Tunova MCP logo, by TunovaCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Tunova
You need:Auth is a single `X-API-Key` header.Sign up at https://tunova.ai/sign-up for 50 free tokens (no card).
MCP endpoint (Streamable HTTP)
https://api.tunova.ai/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

3 of 3 have a description · 0 of 3 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Generate music from text prompts
  • Check the status of a music generation job
  • Wait for a song to complete rendering
  • Generate lyrics only

Source and maintenance

Community listingRegistry 0.1.1
Maintenance checked

Protocol and capabilities

Server
Tunova 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Generate music with Suno. Call generate_song to start a song (returns a job_id; rendering takes 1-3 minutes), then wait_for_song with that job_id to get the audio URL once ready. Use check_song for a one-shot status. Set X-API-Key (your sk_live_ key from https://tunova.ai/keys) in the MCP client headers.

Tools

3 advertised

generate_song
Advertised by the server during the last successful anonymous check.

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.

generate_song input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "tags": {
      "type": "string",
      "description": "Style/genre, e.g. 'lofi hip hop, mellow, rainy'. Most useful in custom mode."
    },
    "model": {
      "enum": [
        "v6",
        "v5.5"
      ],
      "type": "string",
      "description": "Suno model: v6, or v5.5 as a compatibility alias for v6. Optional; the account default is unchanged."
    },
    "title": {
      "type": "string",
      "description": "Song title (custom mode)."
    },
    "custom": {
      "type": "boolean",
      "description": "false (default): describe the song and Suno writes everything. true: `prompt` is the literal lyrics, and `tags`/`title` are used."
    },
    "prompt": {
      "type": "string",
      "description": "What the song should be about (simple mode), or the exact lyrics (when custom=true)."
    },
    "instrumental": {
      "type": "boolean",
      "description": "If true, generate without vocals."
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Optional logical-request id. Reuse it to recover one submit; use a new value to intentionally generate the same song again or retry after a terminal failed job. When omitted, Tunova derives a stable key from the song arguments for safe automatic retries."
    }
  },
  "additionalProperties": false
}
wait_for_song
Advertised by the server during the last successful anonymous check.

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.

wait_for_song input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job_id returned by generate_song."
    },
    "max_wait_seconds": {
      "type": "number",
      "description": "How long to wait before returning (default 45, max 55)."
    }
  },
  "additionalProperties": false
}
check_song
Advertised by the server during the last successful anonymous check.

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.

check_song input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job_id returned by generate_song."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
296 ms
95th percentile latency
296 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 296 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http tunova-mcp https://api.tunova.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add tunova-mcp --url https://api.tunova.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable tunova-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "tunova-mcp": {
      "url": "https://api.tunova.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "tunova-mcp": {
      "type": "streamableHttp",
      "url": "https://api.tunova.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start tunova-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "tunova-mcp": {
      "type": "http",
      "url": "https://api.tunova.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http tunova-mcp https://api.tunova.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.tunova.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "tunova-mcp": {
      "serverUrl": "https://api.tunova.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Tunova MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.