Skip to main content
Glama
joshndala

Music Media MCP Server

by joshndala
OverviewSchemaRelated ServersScoreDiscussions
Python

🎵 Music Media MCP Server

An MCP (Model Context Protocol) server that generates AI-powered music videos. Give it an image or video and it will analyze the visual content, compose a matching soundtrack using Google's Lyria 3 model, merge everything with FFmpeg, and return a playable video artifact.

Pipeline

Source Media (image/video URL)
  → Gemini Vision analyzes the visual content (if no prompt given)
  → Lyria 3 generates a 30-second AI music track
  → FFmpeg merges audio + media into a single .mp4
  → Uploads to Google Cloud Storage
  → Returns an HTML artifact with an inline video player

Related MCP server: media-mcp

Features

  • Auto music prompting — If no music description is provided, Gemini Vision analyzes the image/video and generates a fitting music prompt automatically

  • Multiple media types — Supports images (.jpg, .png, .webp) and videos (.mp4, .mov)

  • Smart video handling — Images loop for 30s, short videos loop to fill, long videos trim to 30s

  • HTML artifact output — Returns a styled video player that MCP-compatible chatbots render inline

  • Cloud Run ready — Deploys to Google Cloud Run with a single command

Prerequisites

  • Python 3.10+

  • FFmpeg installed and on PATH

    # macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt install ffmpeg

  • Google Cloud project with:

    • Vertex AI API enabled (Lyria lyria-002 + Gemini gemini-2.0-flash-001)

    • A GCS bucket for output storage (with public read access or signed URLs)

    • Application Default Credentials:

      gcloud auth application-default login

Setup

  1. Clone and install:

    git clone https://github.com/joshndala/music-media-mcp.git
cd music-media-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .

  2. Configure environment:

    cp .env.example .env
# Edit .env with your GCP project ID and GCS bucket name

  3. Set up GCS CORS (required for video playback in chatbot artifacts):

    # Create cors.json
echo '[{"origin":["*"],"method":["GET"],"responseHeader":["Content-Type","Content-Length","Range"],"maxAgeSeconds":3600}]' > cors.json
gsutil cors set cors.json gs://YOUR_BUCKET_NAME

Running Locally

# stdio transport (for Claude Desktop and other MCP desktop clients)
python server.py

# SSE transport (for web-based MCP clients)
python server.py --transport sse --port 8000

# Test with MCP Inspector
npx @modelcontextprotocol/inspector
# Then connect to http://localhost:8000/sse

Deploying to Cloud Run

# Build the container
gcloud builds submit \
  --tag us-central1-docker.pkg.dev/YOUR_PROJECT/YOUR_REPO/music-media-server \
  --project YOUR_PROJECT

# Deploy
gcloud run deploy music-media-server \
  --image us-central1-docker.pkg.dev/YOUR_PROJECT/YOUR_REPO/music-media-server \
  --region us-central1 \
  --platform managed \
  --allow-unauthenticated \
  --set-env-vars "GCP_PROJECT_ID=YOUR_PROJECT,GCS_BUCKET_NAME=YOUR_BUCKET,GCP_LOCATION=us-central1" \
  --memory 2Gi \
  --timeout 300 \
  --project YOUR_PROJECT

Your SSE endpoint will be at: https://YOUR_SERVICE_URL/sse

MCP Client Configuration

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "music-media": {
      "command": "/path/to/.venv/bin/python",
      "args": ["/path/to/server.py", "--transport", "stdio"],
      "env": {
        "GCP_PROJECT_ID": "your-project-id",
        "GCS_BUCKET_NAME": "your-bucket-name",
        "GCP_LOCATION": "us-central1"
      }
    }
  }
}

Web/Chatbot (SSE)

Point your MCP client to your deployed Cloud Run URL:

https://your-service-url.run.app/sse

Tool Reference

generate_and_merge_media

Parameter

Type

Required

Description

source_media_url

string

✅

Direct URL to a source image or video

music_prompt

string

❌

Music style description (auto-generated if omitted)

Returns: A complete HTML document with an inline video player.

Example prompts:

  • "Upbeat electronic dance music with synth arpeggios"

  • "Calm ambient piano piece evoking a misty morning"

  • "Cinematic orchestral score with soaring strings"

  • (omit for automatic AI analysis)

Environment Variables

Variable

Required

Default

Description

GCP_PROJECT_ID

✅

—

Google Cloud project ID

GCS_BUCKET_NAME

✅

—

GCS bucket for video uploads

GCP_LOCATION

❌

us-central1

Vertex AI region

License

MIT

Available Tools

1 tool
generate_and_merge_mediaA

Generates a music video by combining AI-generated audio with the source image or video.

Args: source_media_url: A publicly accessible URL to a source image or video. music_prompt: Optional music description. If omitted, Gemini generates one.

IMPORTANT: The output of this tool is valid HTML. You MUST display this output to the user by generating a generic HTML Artifact containing the exact code returned by the tool.

ParametersJSON Schema
NameRequiredDescriptionDefault
source_media_urlYes
music_promptNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must cover behavioral traits. It reveals that the output is valid HTML and instructs the agent to display it in an HTML Artifact. This is helpful but could be more explicit about processing time or resource usage. Still, it adequately informs the agent of the output format and expected action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured. It starts with a clear purpose statement, then breaks down parameters, and ends with a critical usage instruction. Every sentence provides valuable information with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's two parameters and the presence of an output schema, the description is complete. It covers input requirements, optional parameters, output format (HTML), and the required user-facing action. No gaps are evident.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must compensate. It explains 'source_media_url' as a publicly accessible URL to source media, and 'music_prompt' as an optional music description that defaults to generation by Gemini. This adds meaningful context beyond the schema's type-only definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Generates a music video by combining AI-generated audio with the source image or video.' This is a specific verb+resource pair, and since there are no sibling tools, differentiation is not needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on the optional music_prompt parameter, stating it can be omitted for Gemini to generate one. It also includes a crucial usage instruction: the output must be displayed via an HTML Artifact. However, it does not discuss when to use this tool versus alternatives (none exist) or any prerequisites beyond public URL accessibility.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion with other tools.

Naming Consistency5/5

With a single tool, naming consistency is trivially maintained. The name uses snake_case and is descriptive.

Tool Count2/5

A single tool for a 'Music Media MCP Server' is too few; the server likely requires multiple tools for different media operations.

Completeness1/5

The tool surface is severely incomplete, lacking separate functionalities for audio generation, video processing, or result retrieval.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/joshndala/music-media-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server