# mediagen

Create images and video from agent requests, edit existing images, and save the results to files. Useful when a project needs generated media without leaving the coding workflow.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 51
- Author: Cripacx
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Cripacx/mediagen
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/mcp/mediagen

## What it does

mediagen routes requests to Google Gemini, OpenAI, or Kie AI. The agent can select a provider or follow your choices for the model, aspect ratio, size, and output filename. It can also edit an existing image and add an AI-generated label to the result.

You need Node.js 20.11 or later and an API key for at least one provider. Run `npx -y mediagen init` to configure a key, then add the MCP server to Claude Code. Avoid passing a key as a command-line argument: the project warns that arguments can remain in shell history and the process list.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mediagen -- npx -y mediagen
```

### Codex

**Platform CLI**
```bash
codex mcp add mediagen -- npx -y mediagen
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mediagen": {
            "command": "npx",
            "args": [
                "-y",
                "mediagen"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mediagen": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "mediagen"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add mediagen npx -y mediagen
```

## When to use it
- generate a hero image from a text brief
- create video with an available provider
- edit an image already in the project
- save generated media under a chosen filename
- label an image as AI-generated

## Example prompts
- Create a wide, moody industrial hero image for the landing page.
- Generate a video from this description and save it in the project folder.
- Edit `hero.png` and add a visible AI-generated label.

## 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