---
title: "Mureka MCP: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/mureka/
description: "Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process."
---

# Mureka MCP: review, setup & limitations · Undominated.ai

> Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process.

[← Explore all mcp servers](/mcp-servers/)

MUSIC GENERATION / Mureka / Skywork AI

# Mureka MCP

Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/SkyworkAI/Mureka-mcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 4 linked sources
 Publisher Mureka / Skywork AI
 Licence [MIT ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/LICENSE)
 Revision 0d4237246db5
 [Read what was—and wasn’t—checked ↓](#review)

“Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process.”

 [Mureka / Skywork AI · upstream description ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process.
- The setup documentation makes this operating boundary explicit: Requests consume Mureka credits and send lyrics/prompts to its service; completed audio is downloaded to the requested local output directory.

### A good fit for

 - Generate lyrics, songs and instrumental music using Mureka and save generated audio through a local MCP process.
- Use Python 3.10 or newer and register uvx mureka-mcp with MUREKA_API_KEY, MUREKA_API_URL=https://api.mureka.ai and a deliberate TIME_OUT_SECONDS value.

### Weigh up before choosing

 - The task-polling timeout does not prove the upstream generation was cancelled. Some HTTP requests and downloads have different or no explicit timeouts; output paths are not sandboxed by the MCP process.
- Package/container parity with the pinned source and transitive dependency security were not established.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - README.md
- LICENSE
- pyproject.toml
- mureka_mcp/api.py

### Our findings

 - Requests consume Mureka credits and send lyrics/prompts to its service; completed audio is downloaded to the requested local output directory.
- The task-polling timeout does not prove the upstream generation was cancelled. Some HTTP requests and downloads have different or no explicit timeouts; output paths are not sandboxed by the MCP process.

### Not established by this review

 - No server installation, authentication, live tool execution or isolation test was performed.
- Package/container parity with the pinned source and transitive dependency security were not established.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/README.md)

DOCUMENTED COMMAND

 uvx mureka-mcp Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Use Python 3.10 or newer and register uvx mureka-mcp with MUREKA_API_KEY, MUREKA_API_URL=https://api.mureka.ai and a deliberate TIME_OUT_SECONDS value.
- Verify the connected account, available tools and target resource before authorizing mutations.

### Before you start

 - Pinned package Python requirement: >=3.10.
- A compatible local process MCP client.
- Requests consume Mureka credits and send lyrics/prompts to its service; completed audio is downloaded to the requested local output directory.

### Compatibility

MCP clients that can launch the documented local process.

### Implementation

Python

### Transports

stdio

### Local process with service or workstation access

 - Requests consume Mureka credits and send lyrics/prompts to its service; completed audio is downloaded to the requested local output directory.

### Cost model

Publisher service entitlements, API usage and infrastructure charges apply where applicable; the MCP source licence does not include external services.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned publisher README and migration notices ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/README.md) Checked 2026-10-14 https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/README.md Supports: description, setup, capabilities, review, limitations
- [Licence text at the reviewed commit ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/LICENSE) Checked 2026-10-14 https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/LICENSE Supports: license
- [Pinned package metadata ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/pyproject.toml) Checked 2026-10-14 https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/pyproject.toml Supports: install, language, review
- [Pinned implementation inspected for launch or permission boundary ↗](https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/mureka_mcp/api.py) Checked 2026-10-14 https://github.com/SkyworkAI/Mureka-mcp/blob/0d4237246db5063cd487351fd36ade39d6bbee41/mureka_mcp/api.py Supports: review, install, access, limitations

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
