@hanoak/unsplash-mcp-server

Search Unsplash Photos

unsplash_search_photos

Read-only

Find Unsplash photos by keyword, applying optional filters for orientation, color, collection, and sort. Returns paginated photo URLs with attribution-ready details and adjustable image sizes.

Instructions

Search Unsplash photos by keyword, with optional filters (orientation, color, order, collections, language). Returns paginated compact photos with URLs and ready-to-use attribution. Content is filtered to "high" safety by default. Read-only. Each photo includes a raw imgix base URL — append params for a custom size/format, e.g. ?w=800&h=600&q=80&fm=webp&fit=crop — plus fixed full/regular/small/thumb sizes.

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": "unsplash_search_photos"
  }
}

Input Schema

Name	Required	Description	Default
`lang`	No	ISO language code for the query, e.g. "en", "es", "fr".
`page`	No	Page number, 1-based.
`color`	No	Filter by dominant color.
`query`	Yes	Search terms (required).
`order_by`	No	Sort order (Unsplash defaults to relevant).
`per_page`	No	Results per page (clamped to a max of 30).
`collections`	No	Comma-separated collection ID(s) to limit results to.
`orientation`	No	Filter by photo orientation.
`content_filter`	No	Content safety filter. Defaults to "high" to exclude potentially unsafe content.	high

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.2.1Aug 24, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses useful behavioral details: output is paginated; photos include compact URLs and attribution; content_filter defaults to 'high' safety; and each photo has a raw imgix base URL with appendable parameters plus fixed sizes. This is meaningful context that helps an agent understand what will happen and what to pass on.

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 brief, front-loaded with the core action, and uses every sentence to add value: the keyword search, the filter list, the return shape, the default safety behavior, the read-only nature, and the imgix URL detail. There is no filler or repetition beyond the mention of the content filter default.

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

Completeness5/5

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

Given the rich input schema (100% coverage) and the absence of an output schema, the description sufficiently fills the gap by describing the output: paginated compact photos, URLs, attribution, imgix URL customization, and fixed sizes. An agent has enough information to select the tool, set required and optional parameters, and interpret the result.

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 coverage is 100%, so parameter semantics are already fully documented. The description adds a general overview of filters and reiterates the high content-filter default, but does not provide additional meaning for individual parameters beyond what the input schema contains.

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 opens with a specific verb and resource: 'Search Unsplash photos by keyword.' It then lists the optional filters and return format, which distinguishes it clearly from sibling search tools like unsplash_search_collections and unsplash_search_users. The purpose is unambiguous.

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

Usage Guidelines4/5

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

The description clearly establishes the tool's use case: searching photos by keyword with optional filters. It provides enough context an agent needs to choose this tool, though it does not explicitly name alternatives or state when not to use it. The context is clear, but exclusions are absent.

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