Skip to main content
MCP server CX Codex

media-gen-mcp — Claude Code MCP server: what it does, how to install

Creates and edits pictures using OpenAI models, and generates videos with Sora or Google Veo straight from your coding assistant.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add --env OPENAI_API_KEY=<OPENAI_API_KEY> --env GEMINI_API_KEY=<GEMINI_API_KEY> --env GOOGLE_API_KEY=<GOOGLE_API_KEY> --env GOOGLE_GENAI_USE_VERTEXAI=<GOOGLE_GENAI_USE_VERTEXAI> --env GOOGLE_CLOUD_PROJECT=<GOOGLE_CLOUD_PROJECT> --transport stdio media-gen-mcp -- npx -y @strato-space/media-gen-mcp
Open on GitHub

What media-gen-mcp does

This server connects coding assistants to OpenAI media APIs and Google Veo. It exposes tools for generating visuals with gpt-image-1.5, altering up to 16 pictures at once, and dispatching video rendering jobs via sora-2 or Google Veo.

The server handles long-running jobs, tracking their status until completion. It downloads finished .mp4 clips, preview thumbnails, and spritesheets directly to local storage, passing outputs back as MCP resource_link references or embedded blocks.

Calls will fail immediately without valid credentials like OPENAI_API_KEY or GEMINI_API_KEY passed into the environment.

What it helps with

  • render images from descriptive prompts using gpt-image-1.5
  • composite and edit up to 16 picture files with inpainting masks
  • submit and poll video rendering jobs in Sora or Google Veo
  • save generated .mp4 video files and thumbnails to local storage

Example prompts for the agent

  • Generate a concept art image of an abandoned space station using openai-images-generate
  • Apply inpainting to banner.png to remove the background logo
  • Start a video render of ocean waves at sunset using Veo and save the resulting .mp4 file

How to install media-gen-mcp

Platform CLI

claude mcp add --env OPENAI_API_KEY=<OPENAI_API_KEY> --env GEMINI_API_KEY=<GEMINI_API_KEY> --env GOOGLE_API_KEY=<GOOGLE_API_KEY> --env GOOGLE_GENAI_USE_VERTEXAI=<GOOGLE_GENAI_USE_VERTEXAI> --env GOOGLE_CLOUD_PROJECT=<GOOGLE_CLOUD_PROJECT> --transport stdio media-gen-mcp -- npx -y @strato-space/media-gen-mcp

Replace <…> with your own values. 9 more environment variables are in the server README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about media-gen-mcp

How to install media-gen-mcp in Claude Code?

Run `claude mcp add media-gen-mcp -e OPENAI_API_KEY=<OPENAI_API_KEY> -e GEMINI_API_KEY=<GEMINI_API_KEY> -e GOOGLE_API_KEY=<GOOGLE_API_KEY> -e AZURE_OPENAI_API_KEY=<AZURE_OPENAI_API_KEY> -- npx -y @strato-space/media-gen-mcp`.

What does media-gen-mcp do?

It provides MCP tools to request image creation and editing via OpenAI, run video jobs in Sora or Google Veo, and manage local media assets.

How does the server deliver generated media?

The tools output files as MCP resource_link items by default or embed them directly as resource objects inside tool results.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor