cbs_save_dataset
AI agents use cbs_save_dataset to create or update resources in Nl Opendata — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nl Opendata environment.
The tool name strongly suggests writing/saving downloaded or processed datasets to local or persistent storage. This is a reversible Write operation (data can be deleted or overwritten later). Without a description, confidence is not higher, but the naming pattern alongside sibling tools (cbs_analyze_*, cbs_query_*) that retrieve and manipulate data suggests this completes a download-and-persist workflow.
From the tool's definition Tool name 'cbs_save_dataset' indicates persisting data to storage; description is empty, limiting certainty about exact behavior and scope.
Attacks that exploit this kind of access
cbs_save_dataset. It is categorised as a Write tool in the Nl Opendata MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nl Opendata MCP server in PolicyLayer and add a rule for cbs_save_dataset: 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 Nl Opendata. Nothing to install.
cbs_save_dataset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cbs_save_dataset 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 cbs_save_dataset. 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.
cbs_save_dataset is provided by the Nl Opendata MCP server (soulnai/nl-opendata-mcp). 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 →