Gemini Media — Claude Code MCP server: generate media
An MCP server that hands your agent Google's generative media models: images, video, speech and music. Useful when assets are needed mid-build.
claude mcp add gemini-media -- docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0What Gemini Media does
It ships as a single Go binary and speaks stdio and Streamable HTTP. Backends are Gemini API or Vertex AI. A built-in catalog tracks model IDs, aliases, lifecycle and prices, and you can override it with a hot-reloaded YAML file.
Tools map to workflows: generate_image and edit_image for stills, tile_image and stitch_tiles for upscaling to 8K, plus separate calls for video, speech and music. Every result carries an estimated cost, and estimate_cost lets you compare options before spending. A ledger records spend, capped by session, daily and monthly budgets.
Credentials come first: a GEMINI_API_KEY from Google AI Studio, or a Google Cloud project with Vertex AI enabled and gcloud auth application-default login run. Agents often skip environment variables, so store the key once with gemini-media-mcp configure --api-key-stdin and check the setup with gemini-media-mcp doctor.
What it helps with
- generate an image from a text prompt inside the agent
- edit an existing picture without touching the rest
- turn a clip into a longer shot
- upscale a photo to 8K tile by tile
- check generation cost before spending
Example prompts for the agent
- Generate a 2K image in 16:9 from the prompt "sunset over the sea"
- Edit
cover.png: remove the background and recolor it blue - How much would a 10-second video cost? Compare options with
estimate_cost
How to install Gemini Media
Platform CLI
claude mcp add gemini-media -- docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0Platform CLI
codex mcp add gemini-media -- docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0Config file
{
"mcpServers": {
"gemini-media": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mordor-forge/gemini-media-mcp:1.1.0"
]
}
}
}Config file
{
"servers": {
"gemini-media": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mordor-forge/gemini-media-mcp:1.1.0"
]
}
}
}Platform CLI
gemini mcp add gemini-media docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0Step 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 Gemini Media
How do I install Gemini Media in Claude Code?
Use the marketplace plugin: run /plugin marketplace add mordor-forge/claude-plugins, then /plugin install gemini-media@mordor-forge. For the server alone there is claude mcp add gemini-media -e GEMINI_API_KEY=... -- gemini-media-mcp.
What does Gemini Media do?
It gives the agent tools for images, video, speech and music on Google models. Outputs can be chained by URI, and each call reports its estimated cost.
What does the server need to run?
A GEMINI_API_KEY from Google AI Studio, or a Google Cloud project with Vertex AI and gcloud auth application-default login completed. The gemini-media-mcp binary must be on your PATH.
