whitney-museum-mcp-server

An MCP server for the Whitney Museum's public API. Search the collection, artists, exhibitions, events and audio guides from Claude Desktop or any MCP client.

Not affiliated with the Whitney Museum of American Art. This is a third-party wrapper around their public API, documented at https://whitney.org/about/website/api.

You don't need an API key, as the Whitney's API is open and unauthenticated.

Install

npx whitney-museum-mcp-server

Or from source:

git clone https://github.com/mildlydiverting/whitney-museum-mcp-server.git
cd whitney-museum-mcp-server
npm install
npm run build

Node 20 or newer.

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "whitney": {
      "command": "npx",
      "args": ["-y", "whitney-museum-mcp-server"]
    }
  }
}

From source, point at the build instead:

{
  "mcpServers": {
    "whitney": {
      "command": "node",
      "args": ["/absolute/path/to/whitney-museum-mcp-server/dist/index.js"]
    }
  }
}

Quit and reopen Claude Desktop. The config doesn't expand ~, so use a full path.

Tools

What to expect

Search returns slim records. Whitney records carry long HTML descriptions and biographies, so search gives you the basics and whitney_get_* gives you everything. Prose is truncated at 2,000 characters, whole responses at 25,000.

Pagination is 30 per page. That's the API's page size. page picks the page, limit trims it further — the default of 10 stops a broad search flooding your context.

Search syntax is Ransack. Predicates nest under q (_eq, _cont, _cont_all_split, _gteq and friends), sorting under q[s]. The typed tools map friendly arguments onto these. whitney_query exposes them raw, for anything the typed tools don't reach.

Artist and artwork fields are mapped explicitly. Exhibitions, events, guides and pages go through a generic summariser instead: HTML stripped, timestamps shortened to dates, relative URLs made absolute, internal foreign keys dropped. The Museum says its field set may change, so nothing is hard-coded that doesn't need to be. Run a search with limit: 1 to see the real field names, then use filters for anything specific.

Known quirks

These are the API's, not the wrapper's.

• sort: "random" doesn't reliably randomise. Asking for three random works returned three consecutive accession numbers by the same artist. If you need genuine randomness, request a random page number instead.

• display_date on artworks is free text — "1915–1931, printed 1976–1977" — so date ranges don't work there. Exhibitions and events have real timestamps, and starts_on_or_after / starts_on_or_before filter on those.

• Living artists have death_year: "0". Don't do arithmetic on it.

• Ransack ignores predicates it doesn't recognise rather than erroring, so a misspelled field silently returns everything. Check your result counts.

Bulk data

For anything at scale, don't page through the API. The Whitney publishes artist and artwork CSVs at https://github.com/whitneymuseum/open-access, released under CC0.

Fun things to do

Get your friendly robot to make connections between Whitney records and other museums using the Getty ULAN and Wikidata MCPs.

(I'm using all these to add links and richer info to my teaching / research notes.)

Licences

Code is released under MIT — see LICENSE.

The underlying data belongs to The Whitney. Material accessed through the API may be protected by copyright and other restrictions. The Whitney permits noncommercial educational and personal use, plus fair use, provided copyright notices are retained and the author and source cited. Read their terms at https://whitney.org/about/website/api before you build anything public on it.

Note the CSV datasets linked above are CC0, which is more permissive than the API terms. Same data, different door.

Thank you

To the Whitney's digital team for publishing an API at all, and for documenting it properly. You are most excellent darlings.