AI agents call lookup_satser 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 tax rates and thresholds for a given year—reference data that is queried but not modified. It fits the Read category: no creation, modification, deletion, code execution, or financial transactions. The low severity reflects minimal blast radius even if called with unexpected arguments, as it only returns factual tax parameters.
From the tool's definition Tool name 'lookup_satser' and description 'Returnerer alle skattesatser og grenser for et gitt inntektsår' (Returns all tax rates and limits for a given income year) indicates retrieval of static reference data.
Attacks that exploit this kind of access
Returnerer alle skattesatser og grenser for et gitt inntektsår. 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 lookup_satser: 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.
lookup_satser 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 lookup_satser 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 lookup_satser. 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.
lookup_satser 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 →