AI agents invoke send_credit_note_email to trigger actions in Sevdesk. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Sending an email is an external operation with real-world side effects (delivering a financial document to a recipient). It cannot be trivially undone once sent. While it involves a financial document (credit note), the primary action is triggering external communication rather than moving money or committing a financial obligation, so Execute is the most appropriate category.
From the tool's definition 'Send a credit note via email from sevdesk' — triggers an external email delivery operation
Attacks that exploit this kind of access
Send a credit note via email from sevdesk. It is categorised as a Execute tool in the Sevdesk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sevdesk MCP server in PolicyLayer and add a rule for send_credit_note_email: 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.
send_credit_note_email is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_credit_note_email 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 send_credit_note_email. 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.
send_credit_note_email 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 →