Atlas / MCP servers / skyworkai / Mureka

MurekaSAFE

mcp/skyworkai/mureka

generate lyrics, song and background music(instrumental). Model Context Protocol (MCP) server.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
—
License
MIT
Stars
118
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://discord.com/invite/nwu9ANqAf5) [](https://x.com/Mureka_AI) [](https://pypi.org/project/mureka-mcp)

Official Mureka Model Context Protocol (MCP) server that enables interaction with powerful lyrics, song and bgm generating APIs. This server allows MCP clients like Claude Desktop, OpenAI Agents and others to generate lyrics, song and background music(instrumental).

Quickstart with Claude Desktop

  1. Get your API key from Mureka.
  2. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.
  3. Go to Claude > Settings > Developer > Edit Config > claudedesktopconfig.json to include the following:
{
"mcpServers": {
"Mureka": {
"command": "uvx",
"args": [
"mureka-mcp"
],
"env": {
"MUREKA_API_KEY": "",
"MUREKA_API_URL": "https://api.mureka.ai",
"TIME_OUT_SECONDS":"300"
}
}
}
}

Then restart the Claude app and see 4 MCP tools available in the window, indicating successful loading

Read from source at commit f846a7f88728OBSERVED · 2026-10-07
02

Connect

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-code
claude mcp add mureka-mcp --env MUREKA_API_KEY=${MUREKA_API_KEY} -- uvx mureka-mcp
claude-desktop
{
  "mcpServers": {
    "mureka-mcp": {
      "command": "uvx",
      "args": [
        "mureka-mcp"
      ],
      "env": {
        "MUREKA_API_KEY": "${MUREKA_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
play_audioreadfile_path = handle_input_file(input_file_path)
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (4)

INFOInventory / provenance · inv.oversize · CWE-1104
assets/16567807049729-9pi6MDiVqTavVUdjf54fmW.mp3
assets/16567807049729-9pi6MDiVqTavVUdjf54fmW.mp3
Why it matters. 4179844 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
assets/16567807049729-D7WVCcxp77Prm8b15HSX1G.mp3
assets/16567807049729-D7WVCcxp77Prm8b15HSX1G.mp3
Why it matters. 4682649 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
assets/demo.jpeg
assets/demo.jpeg
Why it matters. 1043332 bytes not read
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:19
2. Install `uv` (Python package manager), install with `curl -LsSf https://astral.sh/uv/install.sh | sh` or see the `uv` [repo](https://github.com/astral-sh/uv) for additional install methods.

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha f846a7f88728full audit observations/trust-audit/mcp-server/skyworkai__mureka.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07f846a7f88728SAFEB89first audit
06

Questions

What is the Mureka MCP server?

generate lyrics, song and background music(instrumental). Model Context Protocol (MCP) server.

What tools does Mureka expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Mureka safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Mureka need?

It reads MUREKA_API_KEY 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 current is this page?

The grade is for one exact copy of the source (f846a7f88728), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement