AI agents use ksef_update_invoice_draft 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.
This tool modifies an existing invoice draft in a reversible manner—it updates facts or confirmations but does not delete, submit, or irreversibly commit the invoice. Updates to draft state can typically be reverted by subsequent updates.
From the tool's definition Tool name 'ksef_update_invoice_draft' combined with description 'Update an invoice draft' indicates modification of existing invoice data. The word 'update' in both name and description is a clear signal of write operation.
Attacks that exploit this kind of access
Update an invoice draft with user-provided facts or confirmations. 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_update_invoice_draft: 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_update_invoice_draft 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_update_invoice_draft 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_update_invoice_draft. 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_update_invoice_draft 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 →