AI agents call calculate_kryptogevinst 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 pure computational tool that takes crypto transaction data and applies a standard accounting method (FIFO) to calculate gains and losses for tax reporting purposes. It reads/analyzes data and returns calculated results with no side effects, reversible changes, or irreversible actions.
From the tool's definition Tool name 'calculate_kryptogevinst' and description 'Beregner realisert kryptogevinst og -tap per valuta med FIFO-metoden' (Calculates realized crypto gains and losses per currency using FIFO method) indicate a calculation/query operation that processes…
Attacks that exploit this kind of access
Beregner realisert kryptogevinst og -tap per valuta med FIFO-metoden. 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_kryptogevinst: 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_kryptogevinst 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_kryptogevinst 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_kryptogevinst. 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_kryptogevinst 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 →