# Legolev Media MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.legolev%2Fmediamcp
Registry id: `mcp-registry/io.github.legolev/mediamcp`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "legolev-media-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mediamcp"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add legolev-media-mcp-server -- npx -y mediamcp
```

## Tools (6)

- `check_config`: Diagnostics: presence and validity of key, endpoint, default values, writability of output directory. Run first if something doesn't work.
- `check_video_status`: Resumes waiting for a video task by polling_url or id; downloads result when ready.
- `edit_image`: Edit existing image(s) with an instruction. Accepts file paths, https:// and data: URLs; multiple sources for combining images into one composition.
- `generate_image`: Text to image (one or multiple). Saves to disk, returns path and embedded preview. Supports count (up to 4 variations), aspect_ratio, and model override.
- `generate_video`: Text to video or image to video (async task, usually 1-5 minutes). Pass first_frame_image to animate an existing image, last_frame_image for final frame, or ref
- `list_models`: Lists slugs and prices of models supporting images/videos so the agent can pick a model.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
