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/bibekpdl/uswds-mcpWrote 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/bibekpdl/uswds-mcp/claude-code-uswds)<a href="https://agentmods.dev/mcp/bibekpdl/uswds-mcp/claude-code-uswds"><img src="https://agentmods.dev/badge/mcp/bibekpdl/uswds-mcp/claude-code-uswds/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/bibekpdl/uswds-mcp/claude-code-uswds"><img src="https://agentmods.dev/badge/mcp/bibekpdl/uswds-mcp/claude-code-uswds.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
uswds 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 9d ago.
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
{
"uswds": {
"command": "npx",
"args": [
"-y",
"uswds-mcp"
]
}
}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.
- 9d ago First seen · 9 lines scan A 70b6be4f6896
uswds is an MCP server published in the GitHub repository bibekpdl/uswds-mcp (1 stars, last pushed 3mo ago), 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 2026-08-31.
Other mcp servers, from other repositories
layout-doctor-mcp
MCP server "layout-doctor-mcp" as configured in h-kazuki-pixel/layout-doctor-mcp. Runs locally from the layout-doctor-mcp npm package.
flowbite-mcp
MCP server to convert Figma designs to Flowbite UI components in Tailwind CSS. Runs locally from the flowbite-mcp npm package. Needs 1 environment variable to run.
componentize
Screenshot → reusable Tailwind components. MCP Server for AI-powered UI component extraction. Works with Claude, Cursor, Windsurf, Copilot. Runs locally from the @monlohua/componentize npm package.
color-engine-mcp
Six pure, in-memory CSS color tools: parse, convert, WCAG/APCA contrast, gamut map, ramps, solver. Runs locally from the color-engine-mcp npm package.
shadcn
Add components to your apps. Runs locally from the shadcn npm package.
page-design-guide-mcp
MCP server providing modern web design guidance, color psychology, typography, layout patterns, and UI best practices for AI assistants. Runs locally from the page-design-guide-mcp npm package.