AI agents call calculate_aksjefond 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 reads transaction data and performs mathematical calculations to determine tax liability. It is a pure calculation function that produces informational output (tax amounts) without creating, modifying, deleting, or executing arbitrary operations on systems.
From the tool's definition The tool 'calculate_aksjefond' performs calculation ('Beregner skatt') on fund transactions ('verdipapirfond med transaksjons-array'). It takes transaction data as input and computes tax amounts.
Attacks that exploit this kind of access
Beregner skatt for verdipapirfond med transaksjons-array som input. 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_aksjefond: 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_aksjefond 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_aksjefond 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_aksjefond. 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_aksjefond 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 →