snb_get_cube_data
AI agents call snb_get_cube_data to retrieve information from Pypi:swiss Snb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the Swiss National Bank's data warehouse/cube system with no side effects. It matches the Read category pattern of the server's other tools (exchange rates, balance sheets, banking statistics, etc.). The 'get_cube_data' naming convention aligns with query/retrieval semantics. No modification, deletion, execution, or financial transaction capability is indicated.
From the tool's definition Tool name 'snb_get_cube_data' uses the verb 'get', and the server description states it enables AI models to 'query' SNB data. The sibling tools (snb_get_*) all follow a consistent read-only pattern.
Attacks that exploit this kind of access
snb_get_cube_data. It is categorised as a Read tool in the Pypi:swiss Snb MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swiss Snb MCP server in PolicyLayer and add a rule for snb_get_cube_data: 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 Pypi:swiss Snb. Nothing to install.
snb_get_cube_data 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 snb_get_cube_data 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 snb_get_cube_data. 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.
snb_get_cube_data is provided by the Pypi:swiss Snb MCP server (pypi:swiss-snb-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 →