Skip to main content
Glama
serper-search-mcp-server

serper-search-mcp-server

search_images

Search Google Images by query and return image URLs, thumbnails, dimensions, and source pages for visual research, moodboards, or gallery layouts.

Instructions

Google Image search via Serper API. Returns image URLs, thumbnails, dimensions, and source pages. Use layout=gallery for a renderable visual grid (designers/moodboards). Always rich — never compacted.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteNoRestrict to domain (e.g. dribbble.com, behance.net, unsplash.com).
sizeNoFilter by pixel dimensions, client-side via W×H (longest side: small <640, medium <1280, large <2000, xlarge ≥2000; images without dimensions are kept).
queryYesImage search query.
layoutNolist (default) or gallery (renderable ![thumb] grid).list
countryNoISO 3166-1 alpha-2 country code (e.g. "US", "GB"). Default: "US".
ui_langNoUI language (e.g. "en-US"). Default: "en".
providerNoSearch backend: auto (failover chain), serper, tavily, brave, exa, firecrawl. Default: auto.auto
max_charsNoTruncate response to this many characters (0 = no limit).
verbosityNoOutput density: auto (server picks per audience), compact (~800 tokens, dev fast path), standard (KG+Box+10), full (everything, always for places/shopping/images/scholar). Default: auto.auto
safesearchNo"off" | "moderate" | "strict". Default: "moderate".moderate
num_resultsNoResults (1–20, default 10). Note: >10 results uses 2 Serper credits.
orientationNoAspect filter, client-side via W×H (images without dimensions are kept).
search_langNoLanguage code (e.g. "en", "de"). Default: "en".
snippets_onlyNoReturn 1-line snippets only (token-saving for agents). Default: false.
link_resolutionNoGoogle result links beyond the top 3 may come back as google.com/goto redirects. "auto" (default): top 3 resolved, any leftover goto links get a search_id for resolve_links. "all": also resolve every link now (free, but adds ~30 s when goto links are present). "none": fastest, links exactly as Google returns them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv4.1.0
    • removedInput schema / properties / color
      Removed value: -{
      -  "description": "Dominant color filter (e.g. blue, red, green).",
      -  "type": "string"
      -}
    • changedInput schema / properties / orientation / description
      Previous value: -"Aspect filter (client-side via W×H)."New value: +"Aspect filter, client-side via W×H (images without dimensions are kept)."
    • changedInput schema / properties / size / description
      Previous value: -"Image size filter."New value: +"Filter by pixel dimensions, client-side via W×H (longest side: small <640, medium <1280, large <2000, xlarge ≥2000; images without dimensions are kept)."
  2. First observedv4.0.1

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the return fields and the notable "Always rich — never compacted" output behavior, but it says nothing about credit costs (the schema notes >10 results costs 2 Serper credits), rate limits, provider failover, or what happens on empty/blocked results.

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?

Three short sentences, front-loaded with the core purpose and return values before the layout tip. No filler, no restatement of the tool name, and the behavioral caveat is placed last where it does the least harm to scanning.

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?

For a 15-parameter tool with no output schema, the description usefully covers what is returned and how output density behaves, which compensates for the missing output schema. The remaining gap is selection guidance against the many sibling search tools, which an agent must infer.

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%, so the baseline is 3 regardless of description content. The description adds only marginal meaning beyond the schema: it frames layout=gallery as a moodboard/designer affordance, and "never compacted" clarifies how verbosity behaves for this tool specifically.

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

Purpose4/5

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

"Google Image search via Serper API" states a specific verb, resource, and backend, and the second sentence enumerates what comes back (image URLs, thumbnails, dimensions, source pages). It is clearly an image tool, but it never explicitly contrasts itself with search_web or search_videos, so routing is inferred from the resource rather than stated.

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

Usage Guidelines3/5

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

The only actionable guidance is "Use layout=gallery for a renderable visual grid (designers/moodboards)," which is a parameter tip rather than tool-selection guidance. There is no statement of when to prefer this over search_web, search_videos, or scrape, and no exclusions or prerequisites.

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