AI agents call beregn_skatteoppgjoer_nordnet 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 and processes transaction data from Nordnet (a Norwegian brokerage) to calculate tax settlements. It retrieves and analyzes transaction information but does not modify data, execute external commands, delete records, or move money. The classification is Read because it queries and processes existing transaction data for computational purposes.
From the tool's definition Tool description states 'Tar en Nordnet transaksjons-eksport' (takes a Nordnet transaction export), processing either a file path or raw CSV text. No mention of modification, deletion, execution, or financial transactions.
Attacks that exploit this kind of access
Tar en Nordnet transaksjons-eksport (filsti ELLER innlimt rå CSV-tekst),. 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 beregn_skatteoppgjoer_nordnet: 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.
beregn_skatteoppgjoer_nordnet 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 beregn_skatteoppgjoer_nordnet 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 beregn_skatteoppgjoer_nordnet. 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.
beregn_skatteoppgjoer_nordnet 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 →