Execute SPARQL queries against the Nationaal Archief's Linked Open Data.
AI agents invoke na_sparql_query to trigger actions in Nationaal Archief MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes SPARQL queries against an external data endpoint. While SPARQL is typically read-only (SELECT/CONSTRUCT), SPARQL also supports UPDATE operations (INSERT, DELETE) that can modify data. The description says 'execute' and does not restrict to read-only queries.
From the tool's definition 'Execute SPARQL queries against the Nationaal Archief's Linked Open Data'
Attacks that exploit this kind of access
Execute SPARQL queries against the Nationaal Archief's Linked Open Data. It is categorised as a Execute tool in the Nationaal Archief MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nationaal Archief MCP Server MCP server in PolicyLayer and add a rule for na_sparql_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_sparql_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the na_sparql_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_sparql_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_sparql_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 →