AI agents use update_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 existing accounting records reversibly. While it operates in a financial domain and could impact financial records if misused (e.g., changing amounts, dates, or account assignments), the operation is not inherently financial (does not move money) and is not destructive (can be undone by subsequent updates). It is categorized as Write because it creates or modifies data reversibly.
From the tool's definition Tool name 'update_voucher' and description 'Update an existing voucher in sevdesk' explicitly indicates modification of existing data.
Attacks that exploit this kind of access
Update an existing 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 update_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.
update_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 update_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 update_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.
update_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 →