cbs_get_metadata
AI agents call cbs_get_metadata to retrieve information from Nl Opendata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about datasets, which is a read operation with no side effects or ability to modify, delete, or execute code. The empty description slightly reduces confidence, but the naming pattern and server context clearly indicate a data retrieval function. Metadata queries present minimal risk in the context of accessing public Dutch government datasets.
From the tool's definition Tool name 'cbs_get_metadata' indicates retrieval of metadata; server description emphasizes 'accessing and querying' datasets with tools for 'searching, filtering, downloading, and analyzing data'.
Attacks that exploit this kind of access
cbs_get_metadata. It is categorised as a Read tool in the Nl Opendata MCP Server, which means it retrieves data without modifying state.
Register the Nl Opendata MCP server in PolicyLayer and add a rule for cbs_get_metadata: 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_get_metadata 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 cbs_get_metadata 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_get_metadata. 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_get_metadata 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 →