Use after inspect_artwork_image when you want to draw the user
AI agents call navigate_viewer to retrieve information from Rijksmuseum Mcp+ without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests navigation within an image viewer, likely a UI interaction to pan/zoom or move through artwork images. Based on context (used after inspect_artwork_image) it appears to be a read/display operation. However, the description is cut off, lowering confidence. No evidence of write, destructive, financial, or execute behavior.
From the tool's definition 'navigate_viewer' and 'Use after inspect_artwork_image when you want to draw the user' - description is truncated/uninformative
Documented attack patterns abuse exactly the kind of access navigate_viewer gives an agent:
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 navigate_viewer:
{
"version": "1",
"default": "deny",
"tools": {
"navigate_viewer": {}
}
} navigate_viewer is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Use after inspect_artwork_image when you want to draw the user. It is categorised as a Read tool in the Rijksmuseum Mcp+ MCP Server, which means it retrieves data without modifying state.
Register the Rijksmuseum Mcp+ MCP server in PolicyLayer and add a rule for navigate_viewer: 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.
navigate_viewer is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the navigate_viewer 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.
Set action: deny in the PolicyLayer policy for navigate_viewer. 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.
navigate_viewer 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.
Start from Rijksmuseum Mcp+, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Rijksmuseum Mcp+ tools catalogued and risk-classified — across an index of 43,000+ MCP servers.