na_smart_query
AI agents call na_smart_query to retrieve information from Nationaal Archief MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit tool description, classification relies on contextual inference from the server's purpose (archival search and retrieval) and naming patterns of sibling tools. The 'smart_query' name and query-focused server context strongly suggest this retrieves data rather than modifying it.
From the tool's definition Tool name 'na_smart_query' suggests a query operation. Server description indicates tools are for 'searching, browsing, and retrieving archival records' and 'natural language queries'.
Attacks that exploit this kind of access
na_smart_query. It is categorised as a Read tool in the Nationaal Archief MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Nationaal Archief MCP Server MCP server in PolicyLayer and add a rule for na_smart_query: 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 Nationaal Archief MCP Server. Nothing to install.
na_smart_query 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 na_smart_query 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 na_smart_query. 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.
na_smart_query is provided by the Nationaal Archief MCP Server MCP server (w36zl/na_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →