Use when the user has a SPECIFIC artwork (objectNumber) and wants others like it.
AI agents call find_similar 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.
This is a search/retrieval operation that queries the Rijksmuseum collection to find artworks matching similarity criteria. It has no side effects, creates no new data, modifies nothing, and executes no external code. It fits the 'Read' category as a data retrieval function.
From the tool's definition The tool 'find_similar' is used to query and retrieve artworks similar to a specified object, with the description indicating retrieval of data ('wants others like it') based on a specific artwork identifier.
Documented attack patterns abuse exactly the kind of access find_similar 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 find_similar:
{
"version": "1",
"default": "deny",
"tools": {
"find_similar": {}
}
} find_similar 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 when the user has a SPECIFIC artwork (objectNumber) and wants others like it. 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 find_similar: 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.
find_similar 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 find_similar 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 find_similar. 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.
find_similar 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.