RijksmuseumSAFE
Rijksmuseum MCP integration for artwork exploration and analysis
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that provides access to the Rijksmuseum's collection through natural language interactions. This server enables AI models to explore, analyze, and interact with artworks and collections from the Rijksmuseum.
Features
The server provides several tools for interacting with the Rijksmuseum's collection:
1. Search Artworks (search_artwork)
Search and filter artworks using various criteria including:
- Text-based search
- Artist name
- Artwork type
- Materials and techniques
- Time periods
- Colors
- And more
2. Artwork Details (get_artwork_details)
Retrieve comprehensive information about specific artworks, including:
- Basic details (title, artist, dates)
- Physical properties
- Historical context
- Visual information
- Curatorial information
- Exhibition history
3. High-Resolution Images (get_artwork_image)
Access high-resolution image data with deep zoom capabilities:
- Multiple zoom levels
- Tile-based image loading
- Full resolution support
- Position information
4. User Collections (get_user_sets & get_user_set_details)
Explore user-created collections:
- Browse curated sets
- View thematic groupings
- Analyze collection patterns
- Access detailed set information
5. Image Viewing (open_image_in_browser)
Open artwork images directly in your browser for detailed viewing.
6. Artist Timeline (get_artist_timeline)
Generate chronological timelines of artists' works:
- Track artistic development
- Analyze periods and styles
- Study career progression
Example Use Cases
Here are some example queries you can ask the AI when using this server:
Artwork
f2da5db0d23aOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-rijksmuseum --env RIJKSMUSEUM_API_KEY=${RIJKSMUSEUM_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-server-rijksmuseum": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"RIJKSMUSEUM_API_KEY": "${RIJKSMUSEUM_API_KEY}"
}
}
}
}Exposed tools (12)
11 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze-artwork | read | Analyze an artwork |
artist | read | Name of the artist |
artworkId | read | ID of the artwork to analyze |
generate-artist-timeline | read | Generate a chronological timeline of an artist |
get_artist_timeline | read | Get a chronological timeline of an artist |
get_artwork_details | read | Get detailed information about a specific artwork |
get_artwork_image | read | Get image tiles information for an artwork |
get_user_set_details | write | Get details about a specific user collection |
get_user_sets | read | Get collections created by Rijksstudio users |
maxWorks | read | Maximum number of works to include (default: 10) |
open_image_in_browser | read | Open an artwork image URL in your default browser |
search_artwork | read | Search for artworks in the Rijksmuseum collection |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, axios, dotenv, @types/node, typescript
Gates applied: no_behavioural_pass.
f2da5db0d23afull audit observations/trust-audit/mcp-server/r-huijts__rijksmuseum.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | f2da5db0d23a | SAFE | B | 89 | first audit |
Questions
What is the Rijksmuseum MCP server?
Rijksmuseum MCP integration for artwork exploration and analysis
What tools does Rijksmuseum expose?
12 in total: 11 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Rijksmuseum safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Rijksmuseum need?
It reads RIJKSMUSEUM_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Rijksmuseum run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-server-rijksmuseum at 1.0.4.
How current is this page?
The grade is for one exact copy of the source (f2da5db0d23a), read on 2026-10-07. The repository is watched and re-audited when it changes.