Random Design MCP server
io.github.yanislav-igonin/random-design-mcp·v2.1.0Generate randomized English Markdown frontend design directions from curated catalogs.
0 stars40 downloads/wk
Reviews
Write oneNobody has reviewed Random Design yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Random Design tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
generate_design_descriptionGenerate one randomized English Markdown frontend design direction.
get_versionReturn the random-design-mcp package version from package.json for debugging cache or publish state.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan32 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 114 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Random Design compares
Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 65% of 1,337 Media servers
- Tools
- 2
- the typical Media server has 7
- Tools that change things
- 0%
- typical: 4%. Fewer write tools means less an agent can break
- Downloads a week
- 40
- more than 25% of 365 Media servers with a package
What its tools let an agent do: 1 read · 1 create
Install Random Design in Claude Code, Cursor or VS Code
Runs npx -y random-design-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add random-design-mcp -- npx -y random-design-mcp
What the publisher says
From the Random Design repository's README, as published. We do not edit it. Read it on GitHub
Random Design MCP
TypeScript MCP server that returns randomized English Markdown frontend design directions. It uses curated catalogs and optional soft compatibility scoring. It does not call an LLM.
Website: https://random-design-mcp.h0b0.dev
Install
Use the published npm package from any MCP client that supports stdio servers:
{
"mcpServers": {
"random-design": {
"command": "npx",
"args": ["-y", "random-design-mcp"]
}
}
}Tools
generatedesigndescription returns one randomized Markdown design direction. All input fields are optional, but passing context makes the result easier to use:
{
productType?: string;
audience?: string;
priority?: string;
compatibility?: boolean; // defaults to true
}mobile app, or pricing page.
- productType: what you are designing, such as landing page, dashboard,
enterprise buyers.
- audience: who the interface is for, such as developers, founders, or
such as conversion, readability, premium feel, dense data display, or playful experimentation.
- priority: what the design should optimize for or pay extra attention to,
to true, which keeps generated parameters more coherent and practical. Set it to false for unconstrained combinations that can intentionally mix clashing eras, styles, palettes, layouts, and materials.
- compatibility: controls how wild the random combination can be. It defaults
get_version takes no arguments and returns the package version from package.json. Use it to confirm which published or cached MCP package version an MCP client is running.
Development
npm install
npm run build
npm run checkPreview one generated design direction locally:
npm run devOptional preview context:
RANDOM_DESIGN_PRODUCT_TYPE="Landing page" \
RANDOM_DESIGN_AUDIENCE="Developers" \
RANDOM_DESIGN_PRIORITY="Conversion" \
RANDOM_DESIGN_COMPATIBILITY=false \
npm run devNothing above is checked by us. What we check is on the safety report.
Random Design: common questions
- Is Random Design MCP server safe?
- Mostly: it is graded B (82/100). Read the Random Design safety report
- How do I install Random Design?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Random Design need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Random Design maintained?
- The last commit was 152 days ago (2026-06-05). The latest release is v2.1.0.
- What can I use instead of Random Design?
- Servers from other publishers that do the same job: Flanner MCP server, Dembrandt MCP server and KiCad MCP Pro MCP server.
- How does Random Design compare with other Media MCP servers?
- safety score 82/100 (higher than 65% of 1,337 Media servers); tools 2 (the typical Media server has 7); tools that change things 0% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Random Design
Same job from other publishers: the closest match first, then the best rated.
- FlannerKeeps AI coding agents' plan and design markdown managed and versioned, for Claude Code and Codex.not reviewedGrowingA
- DembrandtDesign tokens from any live site: colours, type, spacing, components, drift against a baseline.not reviewedWidely usedB
KiCad MCP ProProduction-grade MCP server for KiCad EDA—PCB design, DRC, simulation, BOM, DFM, and manufacturing.not reviewedEstablishedA- Figma MCP ServerThe Figma MCP server brings Figma design context directly into your AI workflow.not reviewedEstablishedA
- melta UIAI-Ready design system MCP: melta UI tokens, component contracts, 107 rules, check_html self-verifynot reviewedEstablishedA