Enables AI assistants to access the NVIDIA Elements design system, component APIs, design tokens, and UI templates for AI/ML and robotics development.
Also known as NVIDIA/elements, elements-26bdc8, @nvidia-elements/cli
- Stars
- 119
- Tools
- 13
- Downloads, 30 days
- —
- Latest version
- 2.2.17
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is NVIDIA Elements MCP?
NVIDIA Elements enables AI assistants to access the NVIDIA Elements design system, component APIs, design tokens, and UI templates for AI/ML and robotics development. It exposes 13 tools, such as api_list, api_get, api_validate.
Summary generated from the project's README
About NVIDIA Elements MCP server
NVIDIA Elements provides a specialized interface for developers working on AI/ML factories, robotics, and autonomous vehicle interfaces. It functions as both an interactive command-line tool and an MCP server, allowing AI assistants like Claude, Cursor, and Codex to interact directly with the NVIDIA Elements design system. By connecting this server to your local development environment, your AI agent gains access to component APIs, design tokens, and UI templates.
Users can integrate the system by running the nve mcp command and configuring their client with the provided JSON or TOML settings. The server exposes specific tools such as api_list for discovering components, api_tokens_list for accessing semantic CSS properties, and examples_get for retrieving full UI templates. It also supports project management through tools like project_create and project_validate to ensure configuration health. This integration allows for automated linting of HTML and JSON files using the api_validate tool to maintain design consistency.
What you can do with it
- 1Generate UI templatesInstruct an AI agent to build a functional user interface using existing design patterns.
- 2Validate design implementationHave the AI check your HTML or JSON files against official design system linting rules.
- 3Manage design tokensRequest a list of available semantic CSS custom properties for implementing themes.
Written from the project's README. Every use case is checked against a quote from it.
How to install NVIDIA Elements MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall NVIDIA Elements MCP in Claude Code
$ claude mcp add elements-26bdc8 -- npx -y @nvidia-elements/cliInstall NVIDIA Elements MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"elements-26bdc8": {
"command": "npx",
"args": [
"-y",
"@nvidia-elements/cli"
]
}
}
}Install NVIDIA Elements MCP in VS Code
.vscode/mcp.json
{
"servers": {
"elements-26bdc8": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@nvidia-elements/cli"
]
}
}
}Install NVIDIA Elements MCP in VS Code CLI
$ code --add-mcp '{"name":"elements-26bdc8","type":"stdio","command":"npx","args":["-y","@nvidia-elements/cli"]}'Install NVIDIA Elements MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"elements-26bdc8": {
"command": "npx",
"args": [
"-y",
"@nvidia-elements/cli"
]
}
}
}Install NVIDIA Elements MCP in Codex
$ codex mcp add elements-26bdc8 -- npx -y @nvidia-elements/cliInstall NVIDIA Elements MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.elements-26bdc8] command = "npx" args = ["-y", "@nvidia-elements/cli"]
Install NVIDIA Elements MCP in Gemini CLI
$ gemini mcp add -s user elements-26bdc8 npx -- -y @nvidia-elements/cliInstall NVIDIA Elements MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"elements-26bdc8": {
"command": "npx",
"args": [
"-y",
"@nvidia-elements/cli"
]
}
}
}NVIDIA Elements MCP tools 13
Detected from the READMEapi_listapi_getapi_validateapi_imports_getapi_tokens_listpackages_listpackages_getpackages_changelogs_getexamples_listexamples_getproject_createproject_validate
| api_list | — | |
| api_get | — | |
| api_validate | — | |
| api_imports_get | — | |
| api_tokens_list | — | |
| packages_list | — | |
| packages_get | — | |
| packages_changelogs_get | — | |
| examples_list | — | |
| examples_get | — | |
| project_create | — | |
| project_validate | — |
Show all 13 toolsShow fewer tools
project_setup
| project_setup | — |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHub@nvidia-elements/cli
NVIDIA Design System and UI Agent Harness for AI/ML Factories, Robotics, and Autonomous Vehicles.
The @nvidia-elements/cli is a dual-mode command-line tool for the Elements Design System. It provides interactive CLI commands and a Model Context Protocol (MCP) server for AI assistant integration.
Purpose
This package serves two primary modes:
-
Interactive CLI (
nvecommand) - Command-line interface with interactive prompts for:- Component API discovery and search
- Example template browsing and searching
- Template linting and validation
- Project scaffolding and health checks
- Changelog and version information
- Design token access
- Icon name lookup
- Bundled agent skill access
-
MCP Server (
nve mcpcommand) - Model Context Protocol server that:- Exposes MCP-supported tools to AI assistants (Claude, Cursor, etc.)
- Provides context-specific prompts for common tasks
- Enables AI-assisted development with Elements components
- Integrates Elements knowledge directly into AI workflows
Getting Started
The best way to get started is to run the install script.
curl -fsSL https://nvidia.github.io/elements/install.sh | bash
On Windows, run the PowerShell installer.
irm https://nvidia.github.io/elements/install.ps1 | iex
For agents and CI, invoke the canonical path directly: $HOME/.nve/bin/nve on macOS and Linux, or $env:LOCALAPPDATA\nve\bin\nve.exe on Windows.
Alternatively you can install with Node.js and npm.
npm install -g @nvidia-elements/cli
Usage
| Command | Description |
|---|---|
nve |
Show About and help output. |
nve api.list [format] |
Get a list of all available Elements (nve-*) APIs and components. |
nve api.get <names..> [--format <format>] |
Get documentation for one to five known components or attributes (nve-*). |
nve api.validate [paths..] |
Check HTML and JSON from explicit file paths, glob patterns, or standard input (--stdin) using Elements lint rules. |
nve api.imports.get <template> |
Get ESM imports for an HTML template using Elements APIs (nve-*). |
nve api.tokens.list [format] [query] |
Get available semantic CSS custom properties and design tokens for theming. |
nve api.icons.list [format] |
Get available icon names for nve-icon and nve-icon-button. |
nve examples.list [format] |
Get available Elements (nve-*) starter templates, patterns, and examples. |
nve examples.get <id> [format] |
Get the full template of a known example or pattern by ID. |
nve project.create <type> [cwd] [start] |
Create a new starter project. |
nve project.setup [cwd] |
Set up or update a project to use Elements. |
nve project.validate <type> [cwd] |
Check project configuration and dependencies. |
nve packages.list |
Get latest published versions of all Elements packages. |
nve packages.get <name> |
Get details for a specific Elements package. |
nve packages.changelogs.get <name> [format] [limit] |
Retrieve changelog details by package name. |
nve skills.install [--global] |
Install the Elements agent skill in the project or for the current user. |
nve mcp |
Start the MCP server. |
Global Options
| Option | Description |
|---|---|
--help |
Show help. |
--version |
Show version number. |
--upgrade |
Upgrade Elements CLI (nve) to the latest version. |
--debug |
Enable debug output for tools. |
MCP
Quick Setup
The fastest way to configure MCP is with the project.setup command:
nve project.setup
This detects your package manager, configures the MCP server for Cursor, Codex, and Claude Code, and adds Elements core dependencies to the project.
Claude Code
Install to Claude Code by adding the configuration to your .mcp.json file. The file is typically located at ~/.config/claude-code/.mcp.json or %APPDATA%\claude-code\.mcp.json on Windows.
{
"mcpServers": {
"nvidia_elements": {
"description": "NVIDIA Elements UI Design System (nve-*), custom element schemas, APIs and examples",
"command": "nve",
"args": ["mcp"]
}
}
}
After adding the configuration, restart Claude Code for the changes to take effect. The Elements MCP tools are then available for use in your conversations.
Cursor
Install to Cursor with the MCP configuration below.
// .cursor/mcp.json
{
"mcpServers": {
"nvidia_elements": {
"description": "NVIDIA Elements UI Design System (nve-*), custom element schemas, APIs and examples",
"command": "nve",
"args": ["mcp"]
}
}
}
Codex
Install to Codex with the MCP configuration below.
[mcp_servers.nvidia_elements]
description = "NVIDIA Elements UI Design System (nve-*), custom element schemas, APIs and examples"
command = "nve"
args = ["mcp"]
Prompts
| Prompt | Description | Example Prompt |
|---|---|---|
/artifact |
Create a standalone Elements UI artifact | /artifact Create an example login form |
/doctor |
Verify Elements setup and MCP configuration | /doctor |
/create-project |
Create a new Elements starter project | /create-project Create a todo app |
/migrate |
Migrate from deprecated Elements APIs | /migrate Migrate this project from deprecated Elements APIs |
NVIDIA Elements Skill
Elements provides one elements skill with reference files for artifact creation, setup checks, project integration, and migration. Install the complete directory in the current project:
nve skills.install
This writes .agents/skills/elements/ and .claude/skills/elements/. Add --global to install it for the current user at ~/.agents/skills/elements/ instead. The command replaces existing elements directories at the selected destinations so stale references do not remain.
Alternatively, install the Elements agent skill with the open skills CLI:
npx skills add https://github.com/nvidia/elements --skill elements
This route does not install the Elements CLI or configure the MCP server. Use nve project.setup for complete project setup, and continue to use the CLI or MCP tools for deterministic API lookup and template validation.
MCP Tools
| Tool | Description |
|---|---|
api_list |
Get list of all available Elements (nve-*) APIs and components. |
api_get |
Get documentation known components or attributes by name (nve-*). |
api_validate |
Checks HTML and JSON files or supplied content with Elements lint rules. |
api_imports_get |
Get esm imports for a given HTML template using Elements APIs (nve-*). |
api_tokens_list |
Get available semantic CSS custom properties / design tokens for theming. |
packages_list |
Get latest published versions of all Elements packages. |
packages_get |
Get details for a specific Elements package. |
packages_changelogs_get |
Retrieve changelog details by package name. |
examples_list |
Get list of available Elements (nve-*) patterns and examples. |
examples_get |
Get the full template of a known example or pattern by id. |
project_create |
Create a new starter project. |
project_validate |
Check project for configuration issues and dependencies. |
project_setup |
Setup or update a project to use Elements. |
Links
NVIDIA Elements MCP questions
How do I add NVIDIA Elements MCP to Claude Code?
Run claude mcp add elements-26bdc8 -- npx -y @nvidia-elements/cli in your terminal. Add --scope user to make it available in every project.
How do I add NVIDIA Elements MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does NVIDIA Elements MCP provide?
It exposes 13 tools, including api_list, api_get, api_validate, api_imports_get, api_tokens_list.
What can the MCP server do for my AI assistant?
It exposes tools to AI assistants that allow them to list APIs, get component documentation, validate HTML/JSON with lint rules, and retrieve design tokens.
Can I use this with Claude Code?
Yes, you can install it by adding the nvidia_elements configuration to your .mcp.json file.