AI agents use ksef_prepare_invoice to create or update resources in KSeF MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KSeF MCP environment.
The tool creates/builds an invoice XML document and validates it, but explicitly does NOT send it. This is a reversible write/creation action with no submission side effect. The safety gate ('refuses until TEST readiness passes') confirms no external submission occurs. Severity is medium because invoice data is sensitive financial information, but since nothing is transmitted, blast radius is limited.
From the tool's definition Build and validate invoice XML without sending; refuses until TEST readiness passes.
Attacks that exploit this kind of access
Build and validate invoice XML without sending; refuses until TEST readiness passes. It is categorised as a Write tool in the KSeF MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KSeF MCP server in PolicyLayer and add a rule for ksef_prepare_invoice: 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 KSeF MCP. Nothing to install.
ksef_prepare_invoice is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ksef_prepare_invoice 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 ksef_prepare_invoice. 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.
ksef_prepare_invoice is provided by the KSeF MCP server (olegtyshcneko/ksef-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 →