
Random Design
io.github.yanislav-igoninPublished by GitHub account yanislav-igoninv2.1.0Updated Oct 24, 2026
Generate randomized English Markdown frontend design directions from curated catalogs.
Overview
A local MCP server that generates randomized English Markdown frontend design directions from curated catalogs, with optional soft compatibility scoring.
- What you can do
- Generate one randomized Markdown frontend design direction, optionally guided by product type, audience and priority context, with compatibility scoring on or off to control how wild the mix is (generate_design_description). Check which published or cached package version the client is running (get_version).
- When to use it
- Useful when you want fresh, varied starting points for frontend design work — landing pages, dashboards, pricing pages — and want the assistant to propose a concrete direction rather than a generic one. Also handy for deliberately clashing, experimental combinations.
- Requirements
- A local runtime with Node.js and npx, since it runs as a stdio process from the npm package random-design-mcp. No accounts, API keys, environment variables or headers are declared. Desktop MCP clients only.
Installation
In SourceWeft
- Open Random Design in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
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:
Tools
generate_design_description returns one randomized Markdown design direction.
All input fields are optional, but passing context makes the result easier to
use:
productType: what you are designing, such aslanding page,dashboard,mobile app, orpricing page.audience: who the interface is for, such asdevelopers,founders, orenterprise buyers.priority: what the design should optimize for or pay extra attention to, such asconversion,readability,premium feel,dense data display, orplayful experimentation.compatibility: controls how wild the random combination can be. It defaults totrue, which keeps generated parameters more coherent and practical. Set it tofalsefor unconstrained combinations that can intentionally mix clashing eras, styles, palettes, layouts, and materials.
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
Preview one generated design direction locally:
Optional preview context:
Source: README.md at commit 1b03f30
Tools
0Version history
1- v2.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts