AI agents call list_vouchers 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 expense voucher data from the sevdesk accounting system. It performs a read-only operation that returns existing financial records without creating, modifying, deleting, or executing any side effects. While the data retrieved may be financially sensitive (accounting records), the tool itself poses no risk of unintended financial transactions, data corruption, or irreversible changes.
From the tool's definition 'List expense vouchers/receipts from sevdesk' - uses 'list' verb indicating data retrieval with no modification or deletion capability.
Attacks that exploit this kind of access
List expense vouchers/receipts from sevdesk. 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_vouchers: 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_vouchers 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_vouchers 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_vouchers. 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_vouchers 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 →