發送Excel郵件
AI agents use send_excel_email to create or update resources in MCP E-commerce Demo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP E-commerce Demo environment.
The tool sends emails with Excel attachments, which modifies the state of the email system and creates new messages. While not destructive (emails aren't typically permanent or irreversible in a way that cannot be undone), and not directly financial, this is a Write operation since it creates and transmits data.
From the tool's definition send_excel_email suggests sending/transmitting data (email), which is a write operation that creates and dispatches a message.
Attacks that exploit this kind of access
發送Excel郵件. It is categorised as a Write tool in the MCP E-commerce Demo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP E-commerce Demo MCP server in PolicyLayer and add a rule for send_excel_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 MCP E-commerce Demo. Nothing to install.
send_excel_email 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 send_excel_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_excel_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_excel_email is provided by the MCP E-commerce Demo MCP server (uberr2000/mcp_demo). 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 →