AI agents call ksef_list_invoices to retrieve information from KSeF MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and lists invoice metadata without side effects. It is purely informational (Read category). Severity is medium rather than low because invoice metadata in a Polish KSeF e-invoice system may contain sensitive business/financial information (dates, amounts, counterparties, VAT treatment), and an AI agent with unrestricted access could exfiltrate detailed transactional history or intelligence across…
From the tool's definition Tool description states 'Query KSeF invoice metadata for a date range and role' — a retrieval operation with no modification or deletion. The verb 'Query' and 'list' indicate data retrieval only.
Attacks that exploit this kind of access
Query KSeF invoice metadata for a date range and role. It is categorised as a Read tool in the KSeF MCP MCP Server, which means it retrieves data without modifying state.
Register the KSeF MCP server in PolicyLayer and add a rule for ksef_list_invoices: 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_list_invoices 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 ksef_list_invoices 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_list_invoices. 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_list_invoices 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 →