AI agents use enshrine_voucher to create or update resources in Sevdesk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sevdesk environment.
This tool modifies the state of a voucher document by finalizing it, making it a Write operation rather than Read (no retrieval only) or Destructive (the operation is reversible in most accounting systems via document reversal/cancellation). However, finalizing a voucher is a significant financial document state change that could have downstream effects on accounting records and tax compliance.
From the tool's definition Tool description: 'Enshrine (finalize) a voucher in sevdesk' — the verb 'finalize' indicates state transition of a financial document from draft to locked/finalized status, which is a modification operation.
Attacks that exploit this kind of access
Enshrine (finalize) a voucher in sevdesk. It is categorised as a Write tool in the Sevdesk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sevdesk MCP server in PolicyLayer and add a rule for enshrine_voucher: 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 Sevdesk. Nothing to install.
enshrine_voucher 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 enshrine_voucher 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 enshrine_voucher. 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.
enshrine_voucher is provided by the Sevdesk MCP server (codestra/sevdesk-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 →