MCP Media Generator

MCP SSE server with tools to create images and videos using Amazon Nova models via AWS Bedrock.
  • python

4

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You run a Model Context Protocol (MCP) Server that serves image and video creation tools over SSE, enabling clients like LibreChat to discover and use these capabilities directly from your environment.

How to use

Connect your MCP client to the Media Generator MCP Server to access tools for image creation (Amazon Nova Canvas) and video generation (Amazon Nova Reel). Add the server as an MCP endpoint in your client configuration, using the provided URL. After adding the server, restart your MCP client to discover the available tools. Create an agent and attach the media tools to that agent. You can then issue requests through the agent to generate images or videos with the configured models.

How to install

Prerequisites you need before installing this MCP server:

  • Docker and Docker Compose installed on your host.

  • An available Amazon Bedrock account with access to Amazon Nova Canvas and Amazon Nova Reel, and an S3 bucket to store generated videos.

Installation steps you should follow exactly as shown here:

docker-compose up -d

# Verify the service is running and listening on port 8961
curl -sS http://localhost:8961/sse | head -n 5

# Optional: check container status
docker ps --filter "name=mcp_media_generator" --format "table {{.Names}}\t{{.Status}}"

Additional content

Configuration notes: integrate the MCP server with LibreChat by adding a media-creator MCP entry that points to the running container. The example below shows how to reference the server using an HTTP URL, which is the recommended method when hosting the server locally or remotely.

mcpServers:
  media-creator:
    type: http
    url: http://localhost:8961/sse
    args: []
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational