AI agents call tax_jurisdiction_lookup to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tax information without creating, modifying, deleting, executing code, or committing financial obligations. It is a simple lookup query. The low severity reflects that misuse would only expose public or semi-public tax data. Note: this tool appears anomalous in a 3D printer control server context and may be miscategorized or part of a broader manufacturing/commerce platform.
From the tool's definition Tool name 'tax_jurisdiction_lookup' and description 'Look up tax details for a specific region (rate, type, B2B exemptions)' indicate a query/retrieval operation with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Look up tax details for a specific region (rate, type, B2B exemptions). It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for tax_jurisdiction_lookup: 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 Kiln. Nothing to install.
tax_jurisdiction_lookup 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 tax_jurisdiction_lookup 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 tax_jurisdiction_lookup. 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.
tax_jurisdiction_lookup is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →