Skip to main content
Glama

art-institute-chicago-mcp-server

Search artworks

artic_search_artworks
Read-onlyIdempotent

Search the Art Institute of Chicago collection by text and structured filters, ranked by relevance or sorted by date or acquisition year. Text matches all words across titles, artists, descriptions, provenance, and other catalog fields; common English words such as the and of are ignored. Filters combine with AND. Results reach the first 1,000 matches; narrow with filters for more. Set limit to 0 with facets to get only counts. Use artic_lookup_vocabulary for filter values and artic_get_artworks for full records.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "artic_search_artworks"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage to return (1-based); page times the applied limit may not exceed 1,000.
sortNorelevance ranks by query text, or by museum popularity without it. date_asc and date_desc sort by start year: works without one come last, and records with a placeholder start year (outside -8000 to 2100) are left out. acquired_desc (recent acquisitions first) and acquired_asc sort by acquisition fiscal year, with works that have no recorded fiscal year last.relevance
limitNoRequested rows per page (0-1,000); at most 100 are returned. 0 returns only totalCount and facets.
queryNoText matched against titles, artists, descriptions, provenance, and other catalog fields; every word must match, except common English words such as the and of, which are ignored. Supports "exact phrase", -exclude, and a | b.
styleNoStyle title as artic_lookup_vocabulary lists it (case ignored), such as Impressionism; matches preferred or alternate styles.
themeNoTheme title as artic_lookup_vocabulary lists it (case ignored), such as Women artists.
artistNoArtist or culture name matched against every credited artist (all words must match).
facetsNoFacet counts to compute over the filtered set (top 15 values each), any or all of: department, artwork_type, style, subject, classification, material, technique, theme, place_of_origin, gallery, artist. An array or a comma-separated string.
galleryNoGallery where the work is on view, such as Gallery 240 (a bare 240 is read as Gallery 240). Only on-view works carry a gallery.
subjectNoSubject title as artic_lookup_vocabulary lists it (case ignored).
year_toNoLatest year; a work matches when its date span overlaps year_from to year_to. Negative for BCE.
materialNoMaterial title as artic_lookup_vocabulary lists it (case ignored), such as ink or gold leaf.
artist_idNoAgent id from artic_search_artists or an artist facet row; matches preferred and other credits.
has_imageNoOnly works with an image.
techniqueNoTechnique title as artic_lookup_vocabulary lists it (case ignored), such as black-and-white photography or plain weaving.
year_fromNoEarliest year; a work matches when its date span overlaps year_from to year_to. Negative for BCE.
departmentNoDepartment title exactly as artic_lookup_vocabulary lists it (case ignored), such as Prints and Drawings.
acquired_toNoLatest fiscal year in which the museum acquired the work (acquisition_fiscal_year), inclusive. Works with no recorded acquisition year never match.
artwork_typeNoArtwork type title as artic_lookup_vocabulary lists it (case ignored), such as Painting or Print.
on_view_onlyNoOnly works on view at the museum now.
acquired_fromNoEarliest fiscal year in which the museum acquired the work (acquisition_fiscal_year), inclusive. Works with no recorded acquisition year never match, so this filter alone never gives a complete provenance-review set.
classificationNoClassification title as artic_lookup_vocabulary lists it (case ignored), such as oil on canvas or etching.
place_of_originNoPlace of origin as artic_lookup_vocabulary lists it (case ignored), such as france.
public_domain_onlyNoOnly public-domain works, whose images are CC0.

Output Schema

NameRequiredDescriptionDefault
capNoThe limit applied to this page.
pageNoPage returned (1-based).
errorNoPresent when the call failed. Absent on success.
shownNoRows returned on this page.
facetsNoCounts over the filtered set for each requested facet; present only when facets were requested.
noticeNoGuidance when nothing matched, more pages exist, or the reachable window is exhausted.
artworksNoMatching artworks on this page, in ranked or sorted order.
has_moreNoTrue when more matches exist beyond this page.
next_pageNoPage to request next; absent when nothing remains or the next page would pass the first 1,000 matches.
truncatedNoTrue when more matches exist beyond this page.
totalCountNoMatches for the query and filters, before paging.
license_textNoLicense statement from the API for this data, verbatim.
sort_appliedNoOrder applied; popularity when relevance was requested without query text (the museum popularity ranking).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed21 schema fields changed
    • addedInput schema / properties / acquired_from
      Added value: +{
      +  "description": "Earliest fiscal year in which the museum acquired the work (acquisition_fiscal_year), inclusive. Works with no recorded acquisition year never match, so this filter alone never gives a complete provenance-review set.",
      +  "maximum": 2100,
      +  "minimum": 1879,
      +  "type": "integer"
      +}
    • addedInput schema / properties / acquired_to
      Added value: +{
      +  "description": "Latest fiscal year in which the museum acquired the work (acquisition_fiscal_year), inclusive. Works with no recorded acquisition year never match.",
      +  "maximum": 2100,
      +  "minimum": 1879,
      +  "type": "integer"
      +}
    • changedInput schema / properties / facets / description
      Previous value: -"Facet counts to compute over the filtered set (top 15 values each): department, artwork_type, style, subject, classification, place_of_origin, artist. An array or a comma-separated string."New value: +"Facet counts to compute over the filtered set (top 15 values each), any or all of: department, artwork_type, style, subject, classification, material, technique, theme, place_of_origin, gallery, artist. An array or a comma-separated string."
    • changedInput schema / properties / facets / items / enum
      Previous value: -[
      -  "department",
      -  "artwork_type",
      -  "style",
      -  "subject",
      -  "classification",
      -  "place_of_origin",
      -  "artist"
      -]New value: +[
      +  "department",
      +  "artwork_type",
      +  "style",
      +  "subject",
      +  "classification",
      +  "material",
      +  "technique",
      +  "theme",
      +  "place_of_origin",
      +  "gallery",
      +  "artist"
      +]
    • changedInput schema / properties / facets / maxItems
      Previous value: -7New value: +11
    • changedInput schema / properties / limit / description
      Previous value: -"Requested rows per page (0-1,000); at most 12 are returned. 0 returns only totalCount and facets."New value: +"Requested rows per page (0-1,000); at most 100 are returned. 0 returns only totalCount and facets."
    • changedInput schema / properties / query / description
      Previous value: -"Text matched against titles, artists, descriptions, provenance, and other catalog fields; every word must match. Supports \"exact phrase\", -exclude, and a | b."New value: +"Text matched against titles, artists, descriptions, provenance, and other catalog fields; every word must match, except common English words such as the and of, which are ignored. Supports \"exact phrase\", -exclude, and a | b."
    • changedInput schema / properties / sort / description
      Previous value: -"relevance ranks by query text, or by museum popularity without it; date_asc and date_desc sort by start year."New value: +"relevance ranks by query text, or by museum popularity without it. date_asc and date_desc sort by start year: works without one come last, and records with a placeholder start year (outside -8000 to 2100) are left out. acquired_desc (recent acquisitions first) and acquired_asc sort by acquisition fiscal year, with works that have no recorded fiscal year last."
    • changedInput schema / properties / sort / enum
      Previous value: -[
      -  "relevance",
      -  "date_asc",
      -  "date_desc"
      -]New value: +[
      +  "relevance",
      +  "date_asc",
      +  "date_desc",
      +  "acquired_desc",
      +  "acquired_asc"
      +]
    • addedOutput schema / properties / artworks / items / properties / acquisition_fiscal_year
      Added value: +{
      +  "description": "The fiscal year in which the museum acquired the work, which can differ by one from the year in main_reference_number; absent when unrecorded.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / artworks / items / properties / main_reference_number
      Added value: +{
      +  "description": "Museum reference (accession) number; empty when the museum lists none.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / artworks / items / required
      Previous value: -[
      -  "id",
      -  "title",
      -  "is_public_domain",
      -  "is_on_view",
      -  "web_url"
      -]New value: +[
      +  "id",
      +  "title",
      +  "main_reference_number",
      +  "is_public_domain",
      +  "is_on_view",
      +  "web_url"
      +]
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `page_beyond_window`: page times the applied limit exceeds 1,000, past the reachable search window. `invalid_year_range`: year_from is later than year_to. `rate_limited`: The Art Institute API throttled this server and retries ran out, or the shared request queue could not start the call in time. `request_blocked`: The Art Institute API's firewall blocked the request, as it does for markup or script-like text and for bursts of traffic. `upstream_rejected_query`: The Art Institute API rejected a request this server built from valid inputs. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `page_beyond_window`: page times the applied limit exceeds 1,000, past the reachable search window. `invalid_year_range`: year_from is later than year_to, or acquired_from is later than acquired_to. `rate_limited`: The Art Institute API throttled this server and retries ran out, or the shared request queue could not start the call in time. `request_blocked`: The Art Institute API's firewall blocked the request, as it does for markup or script-like text and for bursts of traffic. `upstream_rejected_query`: The Art Institute API rejected a request this server built from valid inputs. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / facets / properties / classification / description
      Previous value: -"Top classification values over the filtered set, most common first."New value: +"Top classification values over the filtered set, most common first. A work can carry several values, so counts overlap."
    • addedOutput schema / properties / facets / properties / gallery
      Added value: +{
      +  "description": "Top gallery values over the filtered set, most common first. Only works on view carry a gallery, each at most one, so the counts cover on-view works alone.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One facet value and its count.",
      +    "properties": {
      +      "count": {
      +        "description": "Matching artworks carrying this value.",
      +        "type": "number"
      +      },
      +      "value": {
      +        "description": "Value as indexed; pass it back verbatim as the gallery filter.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "value",
      +      "count"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / facets / properties / material
      Added value: +{
      +  "description": "Top material values over the filtered set, most common first. A work can carry several values, so counts overlap.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One facet value and its count.",
      +    "properties": {
      +      "count": {
      +        "description": "Matching artworks carrying this value.",
      +        "type": "number"
      +      },
      +      "value": {
      +        "description": "Value as indexed; pass it back verbatim as the material filter.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "value",
      +      "count"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / facets / properties / style / description
      Previous value: -"Top style values over the filtered set, most common first."New value: +"Top style values over the filtered set, most common first. A work can carry several values, so counts overlap."
    • changedOutput schema / properties / facets / properties / subject / description
      Previous value: -"Top subject values over the filtered set, most common first."New value: +"Top subject values over the filtered set, most common first. A work can carry several values, so counts overlap."
    • addedOutput schema / properties / facets / properties / technique
      Added value: +{
      +  "description": "Top technique values over the filtered set, most common first. A work can carry several values, so counts overlap.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One facet value and its count.",
      +    "properties": {
      +      "count": {
      +        "description": "Matching artworks carrying this value.",
      +        "type": "number"
      +      },
      +      "value": {
      +        "description": "Value as indexed; pass it back verbatim as the technique filter.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "value",
      +      "count"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / facets / properties / theme
      Added value: +{
      +  "description": "Top theme values over the filtered set, most common first. A work can carry several values, so counts overlap.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One facet value and its count.",
      +    "properties": {
      +      "count": {
      +        "description": "Matching artworks carrying this value.",
      +        "type": "number"
      +      },
      +      "value": {
      +        "description": "Value as indexed; pass it back verbatim as the theme filter.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "value",
      +      "count"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / sort_applied / enum
      Previous value: -[
      -  "relevance",
      -  "popularity",
      -  "date_asc",
      -  "date_desc"
      -]New value: +[
      +  "relevance",
      +  "popularity",
      +  "date_asc",
      +  "date_desc",
      +  "acquired_desc",
      +  "acquired_asc"
      +]
  2. Changed4 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Rows per page (0-12; capped so a page of long catalog records with every facet stays within common tool-output limits); 0 returns only totalCount and facets."New value: +"Requested rows per page (0-1,000); at most 12 are returned. 0 returns only totalCount and facets."
    • changedInput schema / properties / limit / maximum
      Previous value: -12New value: +1000
    • changedInput schema / properties / page / description
      Previous value: -"Page to return (1-based); page times limit may not exceed 1,000."New value: +"Page to return (1-based); page times the applied limit may not exceed 1,000."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `page_beyond_window`: page times limit exceeds 1,000, past the reachable search window. `invalid_year_range`: year_from is later than year_to. `rate_limited`: The Art Institute API throttled this server and retries ran out, or the shared request queue could not start the call in time. `request_blocked`: The Art Institute API's firewall blocked the request, as it does for markup or script-like text and for bursts of traffic. `upstream_rejected_query`: The Art Institute API rejected a request this server built from valid inputs. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `page_beyond_window`: page times the applied limit exceeds 1,000, past the reachable search window. `invalid_year_range`: year_from is later than year_to. `rate_limited`: The Art Institute API throttled this server and retries ran out, or the shared request queue could not start the call in time. `request_blocked`: The Art Institute API's firewall blocked the request, as it does for markup or script-like text and for bursts of traffic. `upstream_rejected_query`: The Art Institute API rejected a request this server built from valid inputs. Other values are possible when a failure originates below the handler."
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, but the description adds non-obvious behavior: all query words must match across catalog fields, common English words are ignored, filters combine with AND, results are capped at the first 1,000 matches, and limit 0 with facets returns only counts. These details materially help correct invocation.

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 front-loaded with purpose, then adds text-matching behavior, filter combination, result limits, count-only mode, and sibling routing in a compact sequence. Every sentence contributes operational information without filler.

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?

Although the tool has 24 optional parameters, the schema fully documents them and an output schema exists, so the description does not need to explain return fields. It covers the key search semantics, result cap, count-only mode, and alternatives, making it complete enough to invoke correctly.

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 description coverage is 100%, so the schema already carries the main parameter semantics. The description still adds useful cross-parameter behavior not fully captured in individual fields, notably that filters combine with AND and that limit 0 with facets produces count-only results, though much of the query and facet text repeats the schema.

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?

States a specific verb and resource: searching the Art Institute of Chicago collection with text and structured filters, ranked or sorted. It also distinguishes full-record retrieval via artic_get_artworks and filter-value lookup via artic_lookup_vocabulary, so an agent can identify its role without opening the schema.

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?

Explicitly routes filter-value discovery to artic_lookup_vocabulary and full records to artic_get_artworks. It also explains when to narrow the query due to the 1,000-match cap and when to use limit 0 with facets to get only counts.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.