snb_get_cube_metadata
AI agents call snb_get_cube_metadata 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 metadata about SNB data cubes—a purely informational operation with no side effects, data modification, execution of arbitrary code, or financial consequences. Even though the description is empty, the naming convention and server context provide sufficient confidence that this is a read operation.
From the tool's definition Tool name 'snb_get_cube_metadata' indicates a retrieval operation; sibling tools on this server consistently follow a read-only pattern (get_exchange_rates, get_balance_sheet, get_banking_income, etc.) querying public SNB data.
Attacks that exploit this kind of access
snb_get_cube_metadata. 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_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 Pypi:swiss Snb. Nothing to install.
snb_get_cube_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 snb_get_cube_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 snb_get_cube_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.
snb_get_cube_metadata 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 →