AI agents use upload_voucher_file 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.
Uploading a file to a voucher is a write operation that creates or adds data to an existing record. While reversible (files can typically be deleted), it modifies the voucher record's state.
From the tool's definition Tool uploads a file to attach to a voucher, creating new data (file attachment) within the accounting system. The description explicitly states 'upload' and 'attach', which are modification operations that persist data.
Attacks that exploit this kind of access
Upload a file (PDF, image) to attach to a voucher. 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 upload_voucher_file: 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.
upload_voucher_file 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 upload_voucher_file 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 upload_voucher_file. 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.
upload_voucher_file 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 →