Rijksmuseum MCP logo

Rijksmuseum MCP

by r-huijts

Connects AI agents to Rijksmuseum collections for artwork search, research, image inspection, and artist timelines.

Install Rijksmuseum MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "r-huijts-rijksmuseum-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-rijksmuseum"
      ],
      "env": {
        "RIJKSMUSEUM_API_KEY": "YOUR_VALUE_HERE",
        "PORT": "YOUR_VALUE_HERE",
        "LOG_LEVEL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

r-huijts/rijksmuseum-mcp MCP server connects MCP-compatible AI clients to the Rijksmuseum collection through its API. It provides tools for searching artworks, retrieving object details, loading high-resolution image data, browsing user-created sets, opening images in a browser, and generating artist timelines. The server requires a Rijksmuseum API key and can run through an npm package or a local source installation. Reach for it when an agent needs structured Rijksmuseum research, collection discovery, or close visual examination of artworks.

Use cases

  • Search Rijksmuseum artworks by artist, period, color, or technique
  • Retrieve historical and physical details for a specific artwork
  • Inspect high-resolution image regions and visual details
  • Browse thematic user-created museum collections
  • Generate chronological timelines of an artist’s works

Key features

  • Filtered Rijksmuseum artwork search
  • Detailed artwork metadata retrieval
  • High-resolution image and zoom data
  • User set browsing and inspection
  • Browser-based artwork image viewing
  • Artist work timelines

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

10/13 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 11d ago via OSV.dev · mcp-server-rijksmuseum (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars72Stargazers on the source repository.
npm downloads79Package downloads in the last 30 days.
Last commit1y agoMost recent push to the default branch.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Rijksmuseum MCP works

What r-huijts/rijksmuseum-mcp does

The r-huijts/rijksmuseum-mcp MCP server exposes Rijksmuseum collection data to an AI client through natural-language requests. It is intended for artwork discovery, object research, collection browsing, and artist-focused analysis rather than general museum or image-search tasks.

Search can use text and filters such as artist, artwork type, materials and techniques, time period, and color. Detailed object lookups return information including titles, artists, dates, physical properties, historical and curatorial context, visual information, and exhibition history. The server also supports user-created sets, high-resolution image data, browser-based image opening, and chronological artist timelines.

How it works

The server uses the Rijksmuseum API as its collection data source. An MCP-compatible client starts the server and sends tool calls based on the user’s request. The server then translates those requests into collection searches or object-related operations and returns the results to the client.

The available operations include search_artwork, get_artwork_details, get_artwork_image, get_user_sets, get_user_set_details, open_image_in_browser, and get_artist_timeline. Image retrieval includes zoom-related data, image tiles, full-resolution support, and position information where provided by the API. Browser opening is separate from image-data retrieval and is intended for viewing an artwork directly.

Setup and configuration

The documented npm setup is for Claude Desktop. Add an MCP server entry that runs npx -y mcp-server-rijksmuseum and provide the API key through the RIJKSMUSEUM_API_KEY environment variable. The key is obtained from the Rijksmuseum API Portal.

For a source installation, clone the repository, run npm install, copy .env.example to .env, and add the API key. The compiled server can then be started with Node using the built index.js path in the client configuration. The installation path must be replaced with the actual local path, and Claude Desktop must be restarted after configuration changes.

Configuration also lists PORT, which defaults to 3000, and LOG_LEVEL, which defaults to info. The API key is required; the other two variables adjust server behavior.

Tools and capabilities

The r-huijts/rijksmuseum-mcp MCP server supports these documented capabilities:

  • Search and filter artworks by descriptive and collection criteria.
  • Retrieve detailed metadata and curatorial information for an artwork.
  • Access high-resolution image information with multiple zoom levels and tiles.
  • Browse user-created sets and inspect individual set details.
  • Open artwork images in a browser.
  • Build chronological timelines of an artist’s works.

These tools can support questions about Rembrandt, Van Gogh, Vermeer, Dutch Golden Age art, thematic subjects, materials, techniques, and collection groupings when the corresponding information is available through the Rijksmuseum API.

Limitations and notes

The documented client configuration covers Claude Desktop; it does not provide client-specific setup instructions for other MCP applications. Results and available metadata depend on the Rijksmuseum API and its collection records.

The README identifies the project as MIT licensed. API endpoint details are maintained in the Rijksmuseum API documentation linked by the project. Image viewing through open_image_in_browser requires a browser environment, while image data retrieval is handled through the MCP tool interface.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Rijksmuseum MCP

r-huijts/rijksmuseum-mcp is an MCP server that connects AI clients to the Rijksmuseum API and collection. Its main tools search artworks, retrieve artwork details, access high-resolution image data, browse user sets, open images in a browser, and generate artist timelines using a Rijksmuseum API key.

Install it through npm in an MCP client configuration or build it from source. The documented npm method runs `npx -y mcp-server-rijksmuseum`; the source method uses `npm install`, an `.env` file, and the built `index.js`. Both methods require `RIJKSMUSEUM_API_KEY`.

It requires a Rijksmuseum API key stored in `RIJKSMUSEUM_API_KEY`. The README directs users to obtain the key from the Rijksmuseum API Portal and provide it through the MCP client environment or local `.env` file.

Its documented MCP client setup is for Claude Desktop, using either the npm package or a locally built Node entry point.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewRijksmuseum MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/r-huijts-rijksmuseum-mcp?style=directory)](https://allmcps.com/mcp/r-huijts-rijksmuseum-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/r-huijts-rijksmuseum-mcp"><img src="https://allmcps.com/api/badge/r-huijts-rijksmuseum-mcp?style=directory" alt="Rijksmuseum MCP on AllMCPs" /></a>