AI agents call list_voucher_positions to retrieve information from Sevdesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing voucher position data without side effects. It performs a simple lookup operation typical of accounting system data retrieval, presenting minimal risk even if called by an AI agent. No financial transactions, data modifications, or destructive operations are involved.
From the tool's definition Tool name 'list_voucher_positions' and description 'List positions for a voucher' indicate data retrieval only. The 'list' verb is a standard Read operation pattern with no creation, modification, or deletion of data.
Attacks that exploit this kind of access
List positions for a voucher. It is categorised as a Read tool in the Sevdesk MCP Server, which means it retrieves data without modifying state.
Register the Sevdesk MCP server in PolicyLayer and add a rule for list_voucher_positions: 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.
list_voucher_positions 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 list_voucher_positions 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 list_voucher_positions. 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.
list_voucher_positions 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 →