AI agents call get_dataset_status to retrieve information from Macrocosmos MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation to check the status of an existing dataset build. It retrieves information about a process but does not create, modify, execute, delete, or move money. The verb 'get' and the non-destructive nature of status queries place this firmly in the Read category with low severity, as there are no side effects or potential for harm beyond information disclosure.
From the tool's definition Tool name 'get_dataset_status' and description 'Get the status of a dataset build' indicate a query operation that retrieves status information without modifying or deleting data.
Documented attack patterns abuse exactly the kind of access get_dataset_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Macrocosmos MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_dataset_status:
{
"version": "1",
"default": "deny",
"tools": {
"get_dataset_status": {}
}
}get_dataset_status 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.
Get the status of a dataset build. It is categorised as a Read tool in the Macrocosmos MCP MCP Server, which means it retrieves data without modifying state.
Register the Macrocosmos MCP server in PolicyLayer and add a rule for get_dataset_status: 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 Macrocosmos MCP. Nothing to install.
get_dataset_status 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 get_dataset_status 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 get_dataset_status. 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.
get_dataset_status is provided by the Macrocosmos MCP server (macrocosm-os/macrocosmos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Macrocosmos 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.
6 Macrocosmos MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.