artsmia-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_artworksA | Search the Minneapolis Institute of Art (Mia) collection of over 90,000 artworks. Supports Elasticsearch query syntax, field filters (e.g. artist:"Claude Monet", classification:"Paintings", country:"Japan", room:"G355", rights_type:"Public Domain"), pagination (size, from), and sorting. |
| get_artworkA | Get complete curatorial metadata, physical dimensions, medium, provenance, labels, and direct high-resolution image links for a specific artwork by its Mia object ID. |
| get_artworks_batchC | Fetch multiple artworks by a list of object IDs in a single request. |
| get_random_artworkA | Retrieve one or more random artworks from the Minneapolis Institute of Art, optionally filtered by gallery floor/room, artist, medium, or custom query. |
| search_highlightsC | Discover famous masterworks and curated highlight pieces in the Minneapolis Institute of Art permanent collection. |
| get_on_view_artworksA | Find artworks currently on physical exhibition in the museum galleries. Filter by specific gallery room code (e.g., 'G355') or museum floor (1, 2, or 3). |
| get_personA | Look up artist or constituent information by ID, including Wikidata identifier, Wikipedia biography link, and IDs in other major museums (Art Institute of Chicago, MoMA, SAAM). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| curate_tour | Curate a themed walking tour of Mia artworks (e.g. by genre, era, or floor) |
| artwork_critique | Generate a deep curatorial critique and analysis for an artwork ID |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Curated Masterwork Highlights | Top curated highlights in the Minneapolis Institute of Art collection |
| Random Artwork of the Day | A random featured artwork from the collection |
TDQS
Scored across 7 tools
Most tools have clearly distinct purposes: search vs. random vs. highlights vs. on-view vs. person lookup. The only potential confusion is between search_artworks and search_highlights, but their descriptions clarify that one searches the full collection and the other surfaces curated highlights.
All tool names follow a consistent snake_case verb_noun pattern (search_artworks, get_artwork, get_person, etc.). The one compound name, get_on_view_artworks, still fits the established convention.
Seven tools is well-scoped for a museum collection server. Each tool earns its place, covering search, retrieval, batch retrieval, random discovery, highlights, on-view browsing, and person lookup without unnecessary bloat.
For a read-only museum collection API, the surface is complete: full-text search, individual and batch lookup, random exploration, highlights, current exhibitions, and artist metadata. There are no obvious dead ends for typical collection-browsing workflows.