Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Ideelab/uisandboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/ideelab/uisandbox/uisandbox)<a href="https://agentmods.dev/mcp/ideelab/uisandbox/uisandbox"><img src="https://agentmods.dev/badge/mcp/ideelab/uisandbox/uisandbox/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/ideelab/uisandbox/uisandbox"><img src="https://agentmods.dev/badge/mcp/ideelab/uisandbox/uisandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
uisandbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"uisandbox": {
"command": "npx",
"args": [
"-y",
"uisandbox-mcp"
],
"env": {
"UISANDBOX_URL": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 12 lines scan A 328e25aa841f
uisandbox is an MCP server published in the GitHub repository Ideelab/uisandbox (6 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.
Other mcp servers, from other repositories
designscan
Extract a website’s design tokens (colors, type, spacing, shadows) as DESIGN.md, W3C, or CSS. Runs locally from the @designscan/extractor npm package.
dembrandt
Extract design tokens and publicly visible CSS information from any website. Runs locally from the dembrandt npm package.
design-data
MCP server and Claude Code skill for the design-data agent surface — read tools run in-process via wasm. Runs locally from the @adobe/design-data-agent-mcp npm package. Needs 5 environment variables to run.
figma
MCP server "figma", hosted remotely at mcp.figma.com, as configured in adobe/spectrum-design-data.
mimic-ai
Builds Figma from your design system: real components and tokens, enforced, learning every build. Runs locally from the @miapre/mimic-ai npm package.
standby-design-mcp
Generate design systems: OKLCH color palettes, fluid type scales, spacing, shape and icon tokens. Runs locally from the standby-design-mcp npm package.