// SCAN REPORT

Rijksmuseum Mcp+

24 tools. 11 can modify or destroy data without limits.

11 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

11 can modify or destroy data

13 read-only

24 tools total

Community server · catalogue entry verified 11/06/2026

How to control Rijksmuseum Mcp+ ↓

TOOL MAP

What Rijksmuseum Mcp+ exposes to your agents

Read (13) Write / Execute (11) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Rijksmuseum Mcp+ tools

Write · Medium report_type_classification This tool creates or updates classification metadata in the museum's provenance database. Write · Medium report_audit_findings This tool writes/submits audit findings or reports into a system, comparing parser output against raw provenance text. Write · Medium report_event_reclassification This tool reports/submits reclassification requests for provenance events, modifying how events are categorized or merged. Write · Medium report_event_splits This tool reports/submits data about provenance event splits, suggesting it creates or modifies provenance records in the system.

11 of Rijksmuseum Mcp+'s 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Rijksmuseum Mcp+

PolicyLayer is an MCP gateway — it sits between your AI agents and Rijksmuseum Mcp+, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "report_audit_findings": {
    "limits": [
      {
        "counter": "report_audit_findings_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "navigate_viewer": {
    "limits": [
      {
        "counter": "navigate_viewer_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Rijksmuseum Mcp+ — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RIJKSMUSEUM MCP+ →

Free to start. No card required.

FULL CATALOGUE

All 24 Rijksmuseum Mcp+ tools

WRITE 11 tools

Write report_audit_findings Report audit findings comparing parser output against raw provenance text Write report_event_reclassification Report events that should be reclassified as non-provenance or merged with adjacent events Write report_event_splits Report events that should be split into multiple atomic provenance events Write report_field_corrections Report field-level corrections for provenance events with wrong/truncated location or missing receiver parties Write report_party_disambiguation Report the correct party decomposition for a merged/artifact party name Write report_party_extraction Extract parties (sender, receiver, agent) from provenance events where the parser found no parties Write report_pattern_findings Report pattern analysis for unknown provenance segments Write report_position_enrichment Report inferred party positions and transfer categories for ambiguous provenance events Write report_semantic_findings Report from-scratch provenance parsing with reasoning type classification Write report_structural_signals Report structural signals found in unknown provenance segments that could enable deterministic classification Write report_type_classification Classify transfer types for individual unknown provenance events that no parser rule can handle

READ 13 tools

Read navigate_viewer Use after inspect_artwork_image when you want to draw the user Read browse_set Use when you have a setSpec (from list_curated_sets) and want to enumerate its member artworks. Read collection_stats Aggregate counts, percentages, distributions, histograms, totals, summaries, and group-by / count-by / distrib Read find_similar Use when the user has a SPECIFIC artwork (objectNumber) and wants others like it. Read get_artwork_details Use when you need full metadata for a SINGLE artwork (e.g. after a search_artwork / semantic_search / find_sim Read get_recent_changes Use when you need OAI-PMH delta semantics specifically — tracking what changed since a known harvest checkpoin Read inspect_artwork_image Use when YOU (the LLM) need to look at an artwork image or region for visual analysis — identifying details, r Read list_curated_sets Use when you want to discover curated collection sets (193 total) ranging from substantive sub-collections Read search_artwork Use when you have specific filter criteria (subject, material, technique, dates, place, person, theme, …) and Read search_inscriptions Structured search over artwork inscriptions — collector Read search_persons Use when the user has a demographic or structural query about persons (artists, depicted figures, donors): Read search_provenance Use when the user has a provenance question — ownership history, collectors, sales, inheritances, gifts, confi Read semantic_search Use when the user has a free-text concept (

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Rijksmuseum Mcp+

How do I prevent bulk modifications through Rijksmuseum Mcp+? +

The Rijksmuseum Mcp+ server has 11 write tools including report_audit_findings, report_event_reclassification, report_event_splits. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Rijksmuseum Mcp+.

How many tools does the Rijksmuseum Mcp+ MCP server expose? +

24 tools across 3 categories: Execute, Read, Write. 13 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Rijksmuseum Mcp+? +

Register the Rijksmuseum Mcp+ MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Rijksmuseum Mcp+ tool call.

Deterministic rules across all 24 Rijksmuseum Mcp+ tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RIJKSMUSEUM MCP+ →

Free to start. No card required.

24 Rijksmuseum Mcp+ tools catalogued and risk-classified — across an index of 43,000+ MCP servers.