Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@random-design-mcp Generate a design direction for a landing page targeting developers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Use the published npm package from any MCP client that supports stdio servers:
{
"mcpServers": {
"random-design": {
"command": "npx",
"args": ["-y", "random-design-mcp"]
}
}
}Related MCP server: seedflip-mcp
generate_design_description 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
}productType: what you are designing, such as landing page, dashboard,
mobile app, or pricing page.
audience: who the interface is for, such as developers, founders, or
enterprise buyers.
priority: what the design should optimize for or pay extra attention to,
such as conversion, readability, premium feel, dense data display, or
playful experimentation.
compatibility: controls how wild the random combination can be. It defaults
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.
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.
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 devGenerate one randomized English Markdown frontend design direction. Infer optional productType, audience, and priority context from the user's request and pass those fields in English. Set compatibility to false only when the user explicitly wants unconstrained chaotic combinations.
| Name | Required | Description | Default |
|---|---|---|---|
| audience | No | ||
| priority | No | ||
| productType | No | ||
| compatibility | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that results are randomized and that 'compatibility' controls chaos, but does not mention side effects (e.g., mutation), permissions, rate limits, or return value details beyond 'Markdown design direction'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences. First sentence states core action, second provides critical usage condition. No superfluous words, front-loads the essential purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should clarify the return value (does it return the Markdown string or a reference?). It partially covers parameter usage but omits output structure and any behavioral constraints (e.g., rate limits, idempotency).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description explains the semantics of 'compatibility' and states that 'audience', 'priority', and 'productType' should be inferred and passed in English. However, it does not specify allowed values or formats for these string parameters, and the schema has 0% coverage, leaving ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a randomized frontend design direction in English Markdown. It specifies the output format and distinguishes itself from the sibling tool 'get_version' which has a completely different purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives specific guidance on when to set 'compatibility' to false (only on explicit user request for chaotic combinations) and explains that optional fields are inferred from context. While it does not explicitly list alternative tools, the sibling context makes the usage clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the random-design-mcp package version from package.json for debugging cache or publish state.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the returned value and context but omits potential error conditions (e.g., missing package.json) or any side effects. Adequate for a simple read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, 17 words, front-loaded with the action verb 'Return'. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description explains what is returned (package version). For a simple tool, this is sufficient, though a note on version format would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in input schema, so description does not need to add parameter-level details. Baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it returns the package version from package.json and specifies the purpose (debugging cache or publish state). Distinguishes well from the only sibling tool 'generate_design_description'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage scenarios (debugging) but does not explicitly state when not to use or provide alternatives. However, with only one sibling that serves a different purpose, confusion is minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v2.1.0generate_design_descriptionget_versionThe two tools have completely distinct purposes: one generates design descriptions, the other returns a version number. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern using snake_case (generate_design_description, get_version), which is predictable and clear.
With only two tools, the server feels very minimal for its stated purpose of random design generation. While it technically fulfills its core function, the lack of additional tools (e.g., for configuration or output variation) makes it feel incomplete.
The server covers its primary purpose (generating a design description) but lacks any supporting operations like listing past designs, customizing output, or handling multiple generations. The version tool is a minor utility, not core functionality.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Anti-slop design taste for AI coding agents: art directions, section code, 0-100 page critic.
Measured design systems decoded from 588 real products, for coding agents.
Design systems, UI prompts, and layout variations for AI coding tools.
Generate design systems: OKLCH color palettes, fluid type scales, spacing, shape and icon tokens.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yanislav-igonin/random-design-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
