AI agents call calculate_skjermingsfradrag to retrieve information from Skatt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and processes data to perform a tax calculation (shielding deduction for Norwegian dividend tax purposes). It reads input parameters and returns computed results without creating, modifying, deleting, or executing external actions. This is a pure computational/read operation with no side effects.
From the tool's definition Tool name 'calculate_skjermingsfradrag' and description 'Beregner skjermingsfradrag for utbytte på personlig-eide aksjer' (Calculates shielding deduction for dividends on personally-owned shares) — performs a calculation/computation without modifying any data…
Attacks that exploit this kind of access
Beregner skjermingsfradrag for utbytte på personlig-eide aksjer. It is categorised as a Read tool in the Skatt MCP Server, which means it retrieves data without modifying state.
Register the Skatt MCP server in PolicyLayer and add a rule for calculate_skjermingsfradrag: 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 Skatt. Nothing to install.
calculate_skjermingsfradrag 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 calculate_skjermingsfradrag 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 calculate_skjermingsfradrag. 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.
calculate_skjermingsfradrag is provided by the Skatt MCP server (valiantevers/skatt-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 →