report_type_classification

THE RISK

Medium Risk

Why report_type_classification needs a policy

This tool creates or updates classification metadata in the museum's provenance database. While it doesn't delete data (ruling out Destructive) or execute arbitrary code (ruling out Execute), it does modify museum records in a way that could affect how artworks are catalogued and interpreted. The reversible nature and limited scope to classification assignment places it in Write rather than Execute.

From the tool's definition Tool performs 'Classify transfer types' on provenance events, which modifies or sets classification data for museum records.

Documented attack patterns abuse exactly the kind of access report_type_classification gives an agent:

POLICY

How to control report_type_classification

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "report_type_classification": {
      "limits": [
        {
          "counter": "report_type_classification_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

report_type_classification stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Rijksmuseum Mcp+ — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Rijksmuseum Mcp+ 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 miss 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 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

All 24 Rijksmuseum Mcp+ tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about report_type_classification

What does the report_type_classification tool do? +

Classify transfer types for individual unknown provenance events that no parser rule can handle. It is categorised as a Write tool in the Rijksmuseum Mcp+ MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_type_classification? +

Register the Rijksmuseum Mcp+ MCP server in PolicyLayer and add a rule for report_type_classification: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Rijksmuseum Mcp+. Nothing to install.

What risk level is report_type_classification? +

report_type_classification is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit report_type_classification? +

Yes. Add a rate_limit block to the report_type_classification rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block report_type_classification completely? +

Set action: deny in the PolicyLayer policy for report_type_classification. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides report_type_classification? +

report_type_classification is provided by the Rijksmuseum Mcp+ MCP server (kintopp/rijksmuseum-mcp-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Rijksmuseum Mcp+ tool call.

Start from Rijksmuseum Mcp+, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →