# MCP-UI Widgets

> Use this tool when you need to create interactive UI components for AI assistants, such as timers, fact displays, and unit converters, to present dynamic content beyond plain text responses. It solves problems in scenarios like productivity tools, educational displays, and data visualization tasks by providing a customizable and templated HTML widget system. With inputs like user-provided parameters and outputs like interactive UI components, it enables AI assistants to engage users with rich and interactive content.

Canonical page: https://skillsregistry.net/skills/ref-mcp-ui-widgets  
JSON: https://api.skillsregistry.net/v1/skills/ref-mcp-ui-widgets

## Description

Widget MCP server that provides AI assistants with interactive UI components including timers, stopwatches, fact displays, and unit converters through templated HTML widgets. Built with TypeScript and the MCP SDK, it uses a custom HTML templating system that replaces JavaScript configuration objects with user-provided parameters, enabling dynamic widget creation without complex templating syntax. The implementation includes three core tools: timer/stopwatch functionality with audio notifications and editable time displays, fact display widgets for presenting short informational content with custom descriptions, and unit conversion widgets that support real-time multi-unit calculations with customizable formulas. Designed for scenarios where AI assistants need to present interactive content beyond plain text responses, such as productivity tools, educational displays, or data visualization tasks.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ref-mcp-ui-widgets)
- **Repository:** <https://github.com/ref-tools/widget-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ref-mcp-ui-widgets"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ref-mcp-ui-widgets` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ref-mcp-ui-widgets/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt