AI agents call ksef_advise_vat_treatment 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 provides VAT treatment suggestions and identifies missing information without modifying any state. It retrieves or generates advisory data based on input and returns recommendations. The explicit guarantee that it 'never mutates drafts' confirms no write, execute, or destructive operations occur.
From the tool's definition Tool description explicitly states 'Suggest advisory VAT treatment candidates and missing facts; never mutates drafts.' The verb 'suggest' and the promise of non-mutation indicate this is a read-only advisory operation with no side effects.
Attacks that exploit this kind of access
Suggest advisory VAT treatment candidates and missing facts; never mutates drafts. 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_advise_vat_treatment: 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_advise_vat_treatment 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_advise_vat_treatment 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_advise_vat_treatment. 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_advise_vat_treatment 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 →