AI agents call export_datev 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 reads and exports existing accounting data in a specific format (DATEV CSV). It retrieves data without modifying, deleting, or executing anything. The export covers earnings, expenditures, transactions, cashregister, and assets — all read operations. Severity is low as it only reads financial records without moving money or altering state, though the exported data is sensitive accounting information.
From the tool's definition Export booking data in DATEV format from sevdesk (CSV)
Attacks that exploit this kind of access
Export booking data in DATEV format from sevdesk (CSV). Scope: E=Earnings, X=Expenditure, T=Transactions, C=Cashregister, D=Assets. 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 export_datev: 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.
export_datev 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 export_datev 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 export_datev. 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.
export_datev 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 →