Generate a new receive-by-email address for a sandbox
AI agents use reset-sandbox-email-address to create or update resources in Mcp Mailtrap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Mailtrap environment.
This tool generates/regenerates a sandbox email address, which is a write/modification operation. It changes the inbox's receiving address, which could disrupt ongoing tests or cause emails to be delivered to an unexpected address. While not strictly destructive (the old address is replaced rather than data being deleted), it is a reversible modification to configuration.
From the tool's definition Generate a new receive-by-email address for a sandbox
Attacks that exploit this kind of access
Generate a new receive-by-email address for a sandbox. It is categorised as a Write tool in the Mcp Mailtrap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Mailtrap MCP server in PolicyLayer and add a rule for reset-sandbox-email-address: 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 Mailtrap. Nothing to install.
reset-sandbox-email-address 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 reset-sandbox-email-address 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 reset-sandbox-email-address. 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.
reset-sandbox-email-address is provided by the Mcp Mailtrap MCP server (mcp-mailtrap). 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 →