# uxloom MCP server

> Validates UI/UX design completeness, state coverage, and WCAG accessibility compliance through agent-native state machine modeling.

- Repository: https://github.com/uxloom-dev/uxloom
- Page: https://hostedmcp.org/servers/uxloom-dev/uxloom
- Transport: stdio
- Stars: 4
- License: MIT
- Latest version: 0.14.0

## Install

### Claude Code

```sh
claude mcp add uxloom -- npx -y uxloom
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "uxloom": {
      "command": "npx",
      "args": [
        "-y",
        "uxloom"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "uxloom": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "uxloom"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"uxloom","type":"stdio","command":"npx","args":["-y","uxloom"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "uxloom": {
      "command": "npx",
      "args": [
        "-y",
        "uxloom"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add uxloom -- npx -y uxloom
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.uxloom]
command = "npx"
args = ["-y", "uxloom"]
```

### Gemini CLI

```sh
gemini mcp add -s user uxloom npx -- -y uxloom
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "uxloom": {
      "command": "npx",
      "args": [
        "-y",
        "uxloom"
      ]
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `UXLOOM_PROJECT` | no | no | Path to the project file (default: ./uxloom.project.json in the working directory) |

## FAQ

### How can I use UXLoom with AI agents?

You can add it to Claude Code or Codex CLI using npx to enable Agent Skills for design validation.

### Can it audit existing designs from Figma or Penpot?

Yes, the audit command can compare a Figma or Penpot export against your design contract.
