Skip to main content
Glama
mildlydiverting

whitney-museum-mcp-server

Search Whitney artworks

whitney_search_artworks
Read-onlyIdempotent

Search the Whitney Museum's collection of 27,000+ artworks by title, artist, medium, date, or classification. Filter by on-view status, sort results, and get summary records.

Instructions

Search the Whitney Museum's online collection of 27,000+ works.

Returns slim records (id, title, artist, date, medium, classification, on view, first image URL). Call whitney_get_artwork for the full record including dimensions, credit line, description and all images.

Args:

  • title, artist, medium, date (string, optional): substring matches

  • classification (string, optional): exact match, e.g. "Drawings"

  • department ('collection' | 'artport' | 'special', optional)

  • on_view (boolean, optional)

  • sort ('default' | 'title_asc' | 'title_desc' | 'most_viewed' | 'random')

  • page (number, default 1), limit (number, 1-30, default 10)

  • response_format ('markdown' | 'json', default 'markdown')

Returns: { total, count, page, has_more, next_page?, results[], note? }

Examples:

  • "watercolours with flowers in the title" -> title="flower", classification="Drawings", medium="watercolor"

  • "show me something at random from the collection" -> sort="random", limit=3

Notes:

  • Medium spellings follow US usage ("watercolor", "color").

  • Date is free text ("1915-1931, printed 1976-1977"), so filter loosely and check results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoWords in the display date, e.g. '1977'. This is a free-text field, not a number, so ranges are unreliable
pageNo1-based page number; the API returns 30 records per page
sortNoResult ordering; 'most_viewed' ranks by views over the last 30 daysdefault
limitNoMaximum records to return from the fetched page (1-30). Keep this low unless you need the detail — Whitney records are verbose.
titleNoWords appearing in the title (substring match)
artistNoWords appearing in the artist credit line, e.g. 'Divola'
mediumNoWords appearing in the medium, e.g. 'watercolour', 'lithograph'
on_viewNoRestrict to works currently on view
departmentNoWhich collection the work belongs to
classificationNoExact classification; casing matters. Common values: Paintings, Drawings, Prints, Photographs, Sculpture, Installations, Film and Video, Time-based Media
response_formatNoOutput format: 'markdown' for reading, 'json' for machine processingmarkdown

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoAdvisory note about trimming or pagination
pageYesPage that was fetched
countYesRecords returned in this response
totalYesTotal matching records across all pages
sourceYesAttribution for the data, as the Whitney's terms ask for
resultsYesThe records
has_moreYesWhether further pages exist
next_pageNoPage number to request next

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses return shape (slim records, total/count/page/has_more), pagination behavior, US spelling conventions, free-text date caveats, and exact-match behavior for classification. No contradictions 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.

Conciseness4/5

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

The description is well-structured with Args, Returns, Examples, and Notes sections, and the key summary is front-loaded. The Args block partly duplicates the already-complete input schema, which prevents a perfect 5, but the added examples and usage notes are otherwise tightly written.

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?

For an 11-parameter search tool with an output schema and safety annotations, the description is surprisingly complete. It covers return fields, pagination, parameter semantics, edge cases (free-text date, US spelling), and response format selection, so an agent can call it correctly without further inference.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds extra semantic value by mapping natural-language examples to parameters (e.g., 'watercolours with flowers' -> title, classification, medium) and by warning about date free-text and US medium spellings. This goes beyond the schema's per-field descriptions.

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 the Whitney Museum's online collection of 27,000+ works.' It distinguishes itself from sibling tools by explicitly noting that whitney_get_artwork is for full records, and the title clearly signals this is the artworks search tool.

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 gives explicit routing guidance: 'Call whitney_get_artwork for the full record including dimensions, credit line, description and all images.' It also provides concrete query examples that show how to translate user requests into parameter values, making when-to-use practical rather than abstract.

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