Atlas / MCP servers / richawo / Design-components-for-AI-agents

Design-components-for-AI-agentsCAUTION

mcp/richawo/design-components-for-ai-agents

Animated React, Tailwind CSS and React Native components for AI coding agents. Source code, design prompts and JSON briefs, with a shadcn registry, CLI and MCP for Claude Code, Cursor and Codex.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Exposed tools
11 9r · 2w · 0d
Transport
stdio · streamable-http
License
NOASSERTION
Stars
1
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Bring taste to what your agent ships.

Animated React, Tailwind CSS and React Native components for Claude Code, Cursor, Codex and other AI coding agents. Every component comes with source code, a design brief and a JSON prompt.

Explore components · Documentation · Connect your agent · Design principles · Pricing

Why Design for AI?

  • A designed starting point. Give your agent a specific component instead of asking it to invent a design system from a blank prompt.
  • Three ways to build. Install the React or React Native source, paste the design brief, or pass the JSON prompt to your agent. Each describes the same interface.
  • Motion with a purpose. Chart ranges morph, replies stream, navigation moves on springs, and loading resolves into a result. Preview the behaviour before using it.
  • Your code, your stack. Free components are MIT. Components live in your project, with typed props and explicit dependencies. Pro source is licensed separately.

See the components in motion

These are recordings of the actual components. Open any preview to try its controls, see the code or copy its brief. Readers with reduced motion enabled see sti

Read from source at commit 4b0d5a451501OBSERVED · 2026-10-11
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add design-for-ai-mcp --env LICENSE_SECRET=${LICENSE_SECRET} --env PRO_REPO_SSH_KEY=${PRO_REPO_SSH_KEY} --env PRO_REPO_TOKEN=${PRO_REPO_TOKEN} --env STRIPE_WEBHOOK_SECRET=${STRIPE_WEBHOOK_SECRET} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "design-for-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "LICENSE_SECRET": "${LICENSE_SECRET}",
        "PRO_REPO_SSH_KEY": "${PRO_REPO_SSH_KEY}",
        "PRO_REPO_TOKEN": "${PRO_REPO_TOKEN}",
        "STRIPE_WEBHOOK_SECRET": "${STRIPE_WEBHOOK_SECRET}"
      }
    }
  }
}
03

Exposed tools (11)

9 read · 2 write · 0 destructive.

ToolRiskDescription
GuidesreadFixture guides.
get_componentwriteOne component: install command, usage, props, tunable controls (prop ranges and choices), the design prompt, the JSON prompt and the full source file.
get_pagereadAny page of design.yaps.ai as Markdown, e.g.
get_principlesreadThe anti-slop design principles every component follows, plus a checklist. Read before building UI from scratch.
install_commandwriteThe exact command that adds a component to the current project (shadcn CLI for web, curl for React Native).
list_categoriesreadEvery component category with a description and counts of free and Pro components.
outlinereadHeadings and the main claim
rewritereadSame meaning, plainer words
search_componentsreadSearch Design for AI
summarisereadShorten a document or thread
translatereadInto another language
04

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (7 observation(s))
Network
declared (2 observation(s))
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
found

Findings (9)

MEDIUMObfuscation / stealth · obf.zero_width · CWE-506, CWE-94
registry/free/ai-composer-minimal/ai-composer-minimal.tsx:490
{""}
MEDIUMHard-coded secrets · secret.private_key · CWE-798, CWE-321
tests/pro-sync.test.ts:63
const key = "-----BEGIN OPENSSH PRIVATE KEY-----\nprivate-test-key\n-----END OPENSSH PRIVATE KEY-----";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/lib/blog-source.mjs:5
import { LOCALES, asciiSlug } from "../../lib/blog/locales.mjs";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/lib/blog-source.mjs:6
import { BLOG_UI } from "../../lib/blog/ui-copy.mjs";
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@fontsource-variable/bricolage-grotesque, @fontsource-variable/geist, @fontsource-variable/geist-mono, @fontsource/bricolage-grotesque, @fontsource/instrument-serif, gray-matter, lucide-react, marked
Why it matters. 36 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/mcp/package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
docs/COMMERCE.md:66
Use a separate Stripe sandbox for purchases. Test keys, price IDs, portal and signing secret belong together; never point test payments at the production D1 database. A local Worker can receive real s
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
INFOInventory / provenance · inv.oversize · CWE-1104
.github/assets/showcase.gif
.github/assets/showcase.gif
Why it matters. 1069978 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
.github/assets/three-particle-sphere.gif
.github/assets/three-particle-sphere.gif
Why it matters. 1243509 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-11 · audit v0.4.1 · source sha 4b0d5a451501full audit observations/trust-audit/mcp-server/richawo__design-components-for-ai-agents.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-114b0d5a451501CAUTIONB89first audit
06

Questions

What is the Design-components-for-AI-agents MCP server?

Animated React, Tailwind CSS and React Native components for AI coding agents. Source code, design prompts and JSON briefs, with a shadcn registry, CLI and MCP for Claude Code, Cursor and Codex.

What tools does Design-components-for-AI-agents expose?

11 in total: 9 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Design-components-for-AI-agents safe to connect to an agent?

With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does Design-components-for-AI-agents need?

It reads LICENSE_SECRET, PRO_REPO_SSH_KEY, PRO_REPO_TOKEN and STRIPE_WEBHOOK_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Design-components-for-AI-agents run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as design-for-ai-mcp at 0.2.0.

How current is this page?

The grade is for one exact copy of the source (4b0d5a451501), read on 2026-10-11. The repository is watched and re-audited when it changes.

Advertisement