# harvey-design-system-mcp

> harvey-design-system-mcp — thenpceo-harvey-design-system-mcp. Use this tool when you need to ensure on-brand consistency in AI-generated UI, image, motion, and video outputs. It provides a Model Context Protocol server that exposes versioned brand packages as resources, tools, and prompts for AI agents, enabling them to plan and audit outputs without requiring credentials. Ideal for use cases where maintaining brand integrity is crucial, such as marketing, advertising, and media production.

Canonical page: https://skillsregistry.net/skills/thenpceo-harvey-design-system-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thenpceo-harvey-design-system-mcp

## Description

A Model Context Protocol server that exposes a versioned brand package (tokens, rules, recipes, media rights, and audit gates) as resources, tools, and prompts for AI agents. It enables agents to plan and audit on-brand UI, image, motion, and video outputs while remaining read-only and credential-free.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xzn4w0hlv1)
- **Repository:** <https://github.com/thenpceo/harvey-design-system-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": "thenpceo-harvey-design-system-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thenpceo-harvey-design-system-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thenpceo-harvey-design-system-mcp/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