# Gemini 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.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 10
- Author: mordor-forge
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mordor-forge/gemini-media-mcp
- Updated: 2026-10-18
- HTML: https://affpapa.org/en/nevibecode/mcp/gemini-media

## What it 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`.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add gemini-media -- docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0
```

### Codex

**Platform CLI**
```bash
codex mcp add gemini-media -- docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "gemini-media": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/mordor-forge/gemini-media-mcp:1.1.0"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "gemini-media": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/mordor-forge/gemini-media-mcp:1.1.0"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add gemini-media docker run -i --rm ghcr.io/mordor-forge/gemini-media-mcp:1.1.0
```

## When to use it
- 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
- 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`

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26559
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9289

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md