Mureka

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

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio skyworkai-mureka-mcp uvx mureka-mcp \
  --env MUREKA_API_KEY="<insert-your-api-key-here>" \
  --env MUREKA_API_URL="https://api.mureka.ai" \
  --env TIME_OUT_SECONDS="300"

How to use

The Mureka MCP server exposes tools to generate lyrics, songs, and background music (BGMs) through MCP clients like Claude Desktop and OpenAI Agents. When started via uvx with the provided configuration, it connects to Mureka's APIs to produce creative outputs such as song lyrics, full songs, and instrumental BGMs based on user prompts. To enable usage, supply your Mureka API key and ensure the API URL is correct. In Claude Desktop or via the Agents SDK, you’ll see MCP tools that facilitate requests for lyric generation, song composition, and background music creation, each leveraging Mureka’s capabilities. The server acts as a bridge between MCP clients and Mureka’s generation services, translating MCP requests into API calls and returning results back to the client.

How to install

Prerequisites:

Python and uv (uv package manager) installed on your system
An active Mureka API key
Access to the internet to fetch dependencies

Step-by-step installation:

Install uv (Python package manager):
- macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
- Windows: follow uv installation instructions at https://github.com/astral-sh/uv
Install the MCP server dependencies (via uvx, as configured in mcp_config):
- Ensure you have Python and uv installed, then run: uvx install mureka-mcp
Configure environment variables (example):
- MUREKA_API_KEY: <insert-your-api-key-here>
- MUREKA_API_URL: https://api.mureka.ai
- TIME_OUT_SECONDS: 300
Start the MCP server using the configured command:
- The configuration provided in the README uses uvx to run the package name as an MCP server: uvx mureka-mcp
Verify the server is reachable from your MCP client by loading the Mureka MCP tools in Claude Desktop or your OpenAI Agents setup.

Additional notes

Tips and caveats:

You must supply a valid Mureka API key to use the generation tools.
TIME_OUT_SECONDS controls how long the server waits for generation results; adjust as needed for longer requests.
If you encounter authentication errors, double-check the API key, URL, and network connectivity.
The MCP tools expose distinct capabilities (lyrics, songs, and BGMs). Use prompts tailored to each tool for best results.
If using Claude Desktop, add the Mureka MCP configuration under claude_desktop_config.json with the provided fields for seamless loading.
Logs can help diagnose issues; check the Claude or client logs depending on your environment.

Related MCP Servers

mcp-vegalite

MCP server from isaacwasserman/mcp-vegalite-server

github-chat

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

nautex

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

pagerduty

PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

futu-stock

mcp server for futuniuniu stock

mcp -boilerplate

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP