AI agents call calculate_boliggevinst 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 is a computational tool that takes property sale information as input and returns calculated tax values. It does not create, modify, delete, execute code, or move money. It purely retrieves or computes derived information from provided data, making it a Read operation with minimal risk.
From the tool's definition Tool name 'calculate_boliggevinst' and description 'Beregner skattepliktig gevinst eller fradragsberettiget tap ved salg av bolig' (Calculates taxable gain or tax-deductible loss on sale of property).
Attacks that exploit this kind of access
Beregner skattepliktig gevinst eller fradragsberettiget tap ved salg av bolig. 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_boliggevinst: 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_boliggevinst 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_boliggevinst 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_boliggevinst. 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_boliggevinst 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 →