Low Risk

cube_structure

Fetch a Swiss National Bank cube's dimensions/structure (the dimension items / series keys available within the cube). Use this to understand what a cube contains before/after calling get_cube. Verified-live cube IDs: devkua = foreign exchange rates (CHF per currency); zimoma = money market & ref...

Part of the Snb Ch server.

cube_structure is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE SNB CH →

Free to start. No card required.

AI agents call cube_structure to retrieve information from Snb Ch without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though cube_structure only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "cube_structure": {}
  }
}

See the full Snb Ch policy for all 22 tools.

Get this rule live on your own Snb Ch server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SNB CH →

View all 22 tools →

These attack patterns abuse exactly the kind of access cube_structure gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so cube_structure only ever does what you allow.

SECURE SNB CH →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the cube_structure tool do? +

Fetch a Swiss National Bank cube's dimensions/structure (the dimension items / series keys available within the cube). Use this to understand what a cube contains before/after calling get_cube. Verified-live cube IDs: devkua = foreign exchange rates (CHF per currency); zimoma = money market & reference rates incl. SARON; rendoblid = Confederation/euro bond spot interest rates (yield curve); snbmonagg = monetary aggregates (M1/M2/M3, currency in circulation). Defaults to devkua (FX rates).. It is categorised as a Read tool in the Snb Ch MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on cube_structure? +

Register the Snb Ch MCP server in PolicyLayer and add a rule for cube_structure: 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 Snb Ch. Nothing to install.

What risk level is cube_structure? +

cube_structure is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit cube_structure? +

Yes. Add a rate_limit block to the cube_structure 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.

How do I block cube_structure completely? +

Set action: deny in the PolicyLayer policy for cube_structure. 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.

What MCP server provides cube_structure? +

cube_structure is provided by the Snb Ch MCP server (https://gateway.pipeworx.io/snb-ch/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Snb Ch tool call.

Deterministic rules across all 22 Snb Ch tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.