# each::labs

Generate and edit images, video, music and voice through each::labs models. Use it to run media tasks or organization workflows from an AI chat.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: eachlabs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/plugin
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/eachlabs

## What it does

Connect the MCP server to ask an agent to create or edit an image, video, music track or voice recording. It can also crop clips, resize media and convert formats, and run workflows owned by your organization. For a task with several stages, the agent first checks whether an organization workflow can handle it.

You need an each::labs account and must sign in through a browser. Model and workflow runs are billed to the organization selected during sign-in. Check the account before starting: a personal login charges the personal account.

Uploads and results are stored by each::labs, and anyone with a file link can open it. Each file can be up to 100 MB; an upload card accepts up to 50 files unless the selected model allows fewer. The plugin does not include each::sense skills.

## Requirements
- Remote server: `https://mcp.eachlabs.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.eachlabs.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add eachlabs --url https://mcp.eachlabs.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "eachlabs": {
            "url": "https://mcp.eachlabs.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "eachlabs": {
            "type": "http",
            "url": "https://mcp.eachlabs.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http eachlabs https://mcp.eachlabs.ai/mcp
```

## When to use it
- generate an image from a written description
- edit a photo and compare it with the original
- create video or audio with an each::labs model
- trim a clip or convert it to GIF
- run an organization workflow with an uploaded file

## Example prompts
- Generate a photo of a white sneaker on a marble table with soft studio lighting.
- Trim the first 10 seconds of this video and convert the clip to a GIF.
- Find the workflow for a product clip and run it with this photo.

## Similar
- [each-sense](https://affpapa.org/en/nevibecode/skills/each-sense.md) — skill · 227 installs
- [Cutout Labs](https://affpapa.org/en/nevibecode/mcp/cutout-labs.md) — MCP server · ★ 1 repo stars
- [mcp](https://affpapa.org/en/nevibecode/mcp/wavespeedai-mcp.md) — MCP server · ★ 38 repo stars
- [Runway ML](https://affpapa.org/en/nevibecode/mcp/runway-ml.md) — MCP server · ★ 14 repo stars
- [xai-grok-imagine-video](https://affpapa.org/en/nevibecode/skills/xai-grok-imagine-video.md) — skill · 140 installs
- [Remove AI Watermarks](https://affpapa.org/en/nevibecode/mcp/remove-ai-watermarks.md) — MCP server · ★ 6481 repo stars

---
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
