Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kintopp/rijksmuseum-mcp-plus --skill rijksmuseum-mcp-plusgit clone --depth 1 https://github.com/kintopp/rijksmuseum-mcp-plusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kintopp/rijksmuseum-mcp-plus/rijksmuseum-mcp-plus)<a href="https://agentmods.dev/skills/kintopp/rijksmuseum-mcp-plus/rijksmuseum-mcp-plus"><img src="https://agentmods.dev/badge/skills/kintopp/rijksmuseum-mcp-plus/rijksmuseum-mcp-plus/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kintopp/rijksmuseum-mcp-plus/rijksmuseum-mcp-plus"><img src="https://agentmods.dev/badge/skills/kintopp/rijksmuseum-mcp-plus/rijksmuseum-mcp-plus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.12093 |
| Opus 5 | $0.00068 | $0.06046 |
| Sonnet 5 | $0.00027 | $0.02419 |
| Haiku 4.5 | $0.00014 | $0.01209 |
Grade A, and why
rijksmuseum-mcp-plus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rijksmuseum MCP+ Research Skill
Tool Selection Guide
| Question type | Start here |
|---|---|
| "Find works about X" — clear vocabulary concept | search_artwork with subject |
| "Find works about X" — interpretive / atmospheric | semantic_search |
| "Find works depicting [iconographic scene]" | Iconclass server search → search_artwork with iconclass |
| "How many works match X?" | collection_stats for counts/distributions. If you also need IDs (to feed into another tool), follow up with search_artwork(compact: true). |
| "Distribution of X across the collection" | collection_stats with dimension |
| "Top N creators / depicted persons / places" | collection_stats with dimension + topN |
| "Sales by decade" / time series | collection_stats with dimension: "provenanceDecade" |
| "How many artworks have LLM-mediated interpretations?" | collection_stats with dimension: "categoryMethod" |
| "Of artworks with provenance, how many are paintings?" | collection_stats with dimension: "type" + hasProvenance: true |
| "Find persons by demographics / lifespan / profession / birth or death place" | search_persons → feed vocabId to search_artwork(creator=…) |
| "Find/order artworks by physical size or by date" | search_artwork with heightRange/widthRange (e.g. "10-50", "100-", "-30") and/or sort (e.g. "height:desc", "dateEarliest:asc") |
| "Find works near a location / within N km" | search_artwork with nearPlace + nearPlaceRadius, or explicit nearLat/nearLon for any point — see the proximity caveat under Known Limitations |
| "Curatorial theme tags on a work / theme distribution" | search_artwork(theme=…) / collection_stats(dimension="theme") |
| "Cataloguing-channel breakdown (designs, drawings, paintings, prints…)" | search_artwork(sourceType=…) / collection_stats(dimension="sourceType") |
| "What changed since YYYY-MM-DD?" / "Has anything changed since the last harvest checkpoint?" — OAI-PMH delta | get_recent_changes (resumption-token pagination; withdrawn records flagged as deletions) |
| "What does the Rijksmuseum say about this work?" | get_artwork_details |
| "Wikidata Q-id, handle.net URI, other external IDs" | get_artwork_details → work-level externalIds (handle + other); entity-level equivalents[] (e.g. production[].equivalents[], subjects.depictedPersons[].equivalents[]); creator Q-id at production[].personInfo.wikidataId |
| "Scholarly references / citations / bibliography for one work" | get_artwork_bibliography by objectNumber (get_artwork_details → bibliographyCount tells you whether any exist; full: true for all entries) |
| "Which works cite a given publication / reverse bibliography lookup" | find_artworks_citing_publication — the reverse of get_artwork_bibliography; pass a publication URI or id (e.g. from a bibliography entry's publicationUri), full: true for all citing works |
| "Conservation/restoration history, technical examinations (X-ray, dendro, IR, paint samples) for one work" | get_conservation_history by objectNumber |
| "Show this artwork to the user / open the zoomable viewer" | get_artwork_image |
| "Examine this image closely / read this inscription" | inspect_artwork_image |
| "Find works similar to this one" — visual, thematic, lineage, shared subject | find_similar |
| "Find pendants / production stadia / different examples of one design" | find_similar — read the Related Variant column on the resulting HTML page |
| "Find pairs / sets / recto-verso / reproductions / derivatives" | find_similar — read the Related Object column on the resulting HTML page |
| "Show me a curated group of works on X" | list_curated_sets → browse_set |
| "Who owned this work / trace its ownership chain" | search_provenance with objectNumber |
| "Which works passed through collector X?" | search_provenance with party |
| "Find confiscations / sales / transfers in city Y" | search_provenance with transferType, location |
| "How long did family X hold their collection?" | search_provenance with layer: "periods", ownerName |
| "Works bearing collector mark / Lugt N, or a handwritten signature on the recto" | search_inscriptions with collectorMark / facet combo (inscriptionType, placement, technique) |
| "What is actually written/signed on this work?" | get_artwork_details → parsedInscriptions / inscriptionSummary, or search_inscriptions with transcribedText |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed 19aef2eddfad
- 13d ago First seen · 422 lines · 136 tokens per session scan A 71434e5a9850
rijksmuseum-mcp-plus is a skill published in the GitHub repository kintopp/rijksmuseum-mcp-plus (16 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 12,093 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
classification-at-scale
Classify an internal catalog against a standard taxonomy at scale using deterministic providers, tri-state signals, batch group review, and a trust flywheel — LLM judgment only for configs, ambiguous tails, and critique.
setup
Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
overlay-and-fit
Create an overlay from a published reference state, use the inherited state plus any applied kit with the lowest-friction path, and only add local config or code when the current overlay is not enough.
create-state
Create a new Cruxible state from raw domain data through staged graph, workflow, query, and review-loop design.