Tutorial: Art & Museum Collections

Media

Data source: Metropolitan Museum of Art Collection API, Art Institute of Chicago API

Overview

Art & Museum Collections wraps Metropolitan Museum of Art Collection API, Art Institute of Chicago API, handling authentication, pagination, and rate limits for you. This tutorial covers all 4 tools with working code examples you can copy and run.

Prerequisites

Sign up at https://context.gnist.ai/signup for a free API key (100 calls/day).
Choose your integration method: MCP protocol or REST API.

Connect via MCP

Add to your MCP client config (Claude Desktop, Cursor, etc.):

MCP Config

{
  "mcpServers": {
    "gnist-museum": {
      "url": "https://context.gnist.ai/mcp/museum/",
      "headers": {
        "Gnist-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Tools (4)

`search_artworks`

Search artworks across the Metropolitan Museum of Art (470K+ objects) and Art Institute of Chicago (120K+ objects). Returns titles, artists, dates, media, dimensions, departments, images, and more. Search both institutions at once or filter to one. Examples: search_artworks("impressionism") → Impressionist works from both museums search_artworks("armor", institution="met", department_id=4) → Arms and Armor at the Met search_artworks("Monet water lilies", institution="aic") → Monet at Art Institute of Chicago Returns: total, results (list of artworks with metadata and image URLs), query.

Parameter	Type	Required	Description
`query`	string	required	Search term — artist, title, style, subject. Example: 'Van Gogh sunflowers'.
`institution`	any	optional	Filter by institution: 'met' (Metropolitan Museum of Art) or 'aic' (Art Institute of Chicago). Omit to search both.
`department_id`	any	optional	Met Museum department ID filter (use get_departments to list). Only applies when institution='met'.
`is_highlight`	any	optional	Only return highlighted/notable works. Met only.
`has_images`	any	optional	Only return works with images. Met only.
`medium`	any	optional	Filter by medium, e.g. 'Paintings', 'Sculpture', 'Photographs'. Met only.
`date_begin`	any	optional	Start year filter, e.g. 1800. Met only.
`date_end`	any	optional	End year filter, e.g. 1900. Met only.
`limit`	integer	optional	Max results to return (1-10). (default: `5`)

curl -X POST "https://context.gnist.ai/mcp/museum/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "search_artworks", "arguments": {"query": "renewable energy"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/museum/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'query': 'renewable energy'},
            'name': 'search_artworks'}},
)
print(resp.json())

`get_artwork`

Get full details for a specific artwork by ID and institution. Returns complete metadata: title, artist, dates, medium, dimensions, department, classification, culture, period, credit line, public domain status, image URLs, tags, and Wikidata links (Met) or provenance, exhibition history, and description (AIC). Examples: get_artwork(436535, "met") → Van Gogh's Wheat Field with Cypresses get_artwork(27992, "aic") → Seurat's A Sunday on La Grande Jatte Returns: Full artwork metadata dict.

Parameter	Type	Required	Description
`object_id`	integer	required	Artwork ID from the institution.
`institution`	string	required	Institution: 'met' (Metropolitan Museum) or 'aic' (Art Institute of Chicago).

curl -X POST "https://context.gnist.ai/mcp/museum/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_artwork", "arguments": {"object_id": 5, "institution": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/museum/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'institution': 'example', 'object_id': 5},
            'name': 'get_artwork'}},
)
print(resp.json())

`get_departments`

List all curatorial departments at the Metropolitan Museum of Art. Returns department IDs and names. Use department IDs to filter search_artworks results. Departments include: American Decorative Arts, Ancient West Asian Art, Arms and Armor, Asian Art, The Cloisters, European Paintings, Egyptian Art, Photographs, Modern Art, and more. Returns: departments (list of {id, name}).

curl -X POST "https://context.gnist.ai/mcp/museum/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_departments", "arguments": {}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/museum/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {}, 'name': 'get_departments'}},
)
print(resp.json())

`report_feedback`

Report a bug, feature request, or general feedback for this data source. Use this when something doesn't work as expected, when you'd like a new feature, or when you have suggestions for improvement. Args: feedback: Describe the issue or suggestion. feedback_type: One of 'bug', 'feature_request', or 'general'.

Parameter	Type	Required	Description
`feedback`	string	required
`feedback_type`	string	optional	(default: `general`)

curl -X POST "https://context.gnist.ai/mcp/museum/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "report_feedback", "arguments": {"feedback": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/museum/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'feedback': 'example'}, 'name': 'report_feedback'}},
)
print(resp.json())

Common Patterns

Search then retrieve
Use search_artworks to find items, then get_artwork to get full details. This two-step pattern is common for exploring data before drilling down.

Pagination
Several tools support limit, offset, or page parameters. Start with small limits during development, then increase for production queries.

FAQ

What data does Art & Museum Collections provide?

Search 470K+ artworks from the Metropolitan Museum of Art and 120K+ from the Art Institute of Chicago — titles, artists, dates, media, images, and full provenance. It exposes 4 tools: search_artworks, get_artwork, get_departments, report_feedback.

What do I need to get started?

A Gnist API key (free tier: 100 calls/day). Sign up at https://context.gnist.ai/signup.

What format does the Art & Museum Collections API return?

JSON, via either MCP protocol (JSON-RPC 2.0) or REST API.