Skip to main content
Glama
YonasValentin

Design Inspiration MCP Server

Search design images

design_search_images
Read-onlyIdempotent

Search for UI design inspiration across Dribbble, Behance, Awwwards, Mobbin, and Pinterest. Find images with URLs, dimensions, and source links using specific design queries like 'dashboard dark mode' or 'mobile onboarding flow'.

Instructions

Image search across Dribbble, Behance, Awwwards, Mobbin, and Pinterest. Returns image URLs, dimensions, and source links. Use specific UI terms ("fintech dashboard dark mode") over vague ones ("nice design").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesUI design search query. Examples: "dashboard dark mode", "mobile onboarding flow", "saas pricing page"
sitesNoFilter to specific design sites. Empty array searches all sites. Options: dribbble, behance, awwwards, mobbin, pinterest
numNoNumber of image results to return (1-40, default: 10)

Implementation Reference

  • The handler implementation for the `design_search_images` tool, including the search logic using `serperRequest` and result formatting.
    server.registerTool("design_search_images", {
      title: "Search design images",
      description: `Image search across Dribbble, Behance, Awwwards, Mobbin, and Pinterest. Returns image URLs, dimensions, and source links. Use specific UI terms ("fintech dashboard dark mode") over vague ones ("nice design").`,
      inputSchema: SearchImagesInputSchema,
      annotations: {
        readOnlyHint: true,
        destructiveHint: false,
        idempotentHint: true,
        openWorldHint: true,
      },
    }, async (params: SearchImagesInput) => {
      try {
        const siteQuery = buildSiteQuery(params.query + " UI design", params.sites);
        const data = await serperRequest<SerperImagesResponse>("/images", {
          q: siteQuery,
          num: params.num,
        });
    
        const images = data.images || [];
        const text = formatImageResults(images, params.query);
    
        return {
          content: [{ type: "text" as const, text }],
          structuredContent: {
            query: params.query,
            count: images.length,
            images: images.map((img) => ({
              title: img.title,
              imageUrl: img.imageUrl,
              thumbnailUrl: img.thumbnailUrl,
              source: img.source,
              link: img.link,
              width: img.imageWidth,
              height: img.imageHeight,
            })),
          },
        };
      } catch (error) {
  • Input validation schema for the `design_search_images` tool using Zod.
        ),
      sites: z
        .array(z.enum(["dribbble", "behance", "awwwards", "mobbin", "pinterest"]))
        .default([])
        .describe(
          "Filter to specific design sites. Empty array searches all sites. Options: dribbble, behance, awwwards, mobbin, pinterest"
        ),
      num: z
        .number()
        .int()
        .min(1)
        .max(40)
        .default(10)
        .describe("Number of image results to return (1-40, default: 10)"),
    })
    .strict();
  • src/index.ts:162-162 (registration)
    Registration of the `design_search_images` tool.
    server.registerTool("design_search_images", {
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety and behavior. The description adds context about the search scope (five specific sites) and result format (URLs, dimensions, source links), which is useful but doesn't provide rich behavioral details like rate limits or authentication needs. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core functionality and followed by usage guidance. Every sentence earns its place with no wasted words, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 parameters, no output schema), the description is mostly complete. It covers purpose, usage, and result format, but lacks details on error handling or pagination. With annotations providing safety context, it's sufficient but could be slightly enhanced for full completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter well-documented in the schema. The description adds minimal value beyond the schema by implying the query should be UI-focused and specific, but doesn't explain parameter semantics in detail. Baseline 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for images across five specific design platforms (Dribbble, Behance, Awwwards, Mobbin, Pinterest) and returns specific data (image URLs, dimensions, source links). It distinguishes itself from sibling tools like 'design_search_references' and 'design_search_styles' by focusing on image search rather than references or styles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool by recommending specific UI terms (e.g., 'fintech dashboard dark mode') over vague ones (e.g., 'nice design'). It doesn't mention alternatives, but the context of sibling tools (design_search_references, design_search_styles) implies differentiation, and the guidance is clear for this specific use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/YonasValentin/design-inspiration-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server