Get the plain-text body of a sandbox message.
AI agents call get-sandbox-message-text to retrieve information from Mcp Mailtrap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and retrieves existing sandbox message content. Sandbox environments are isolated and non-production, so even if misused, the blast radius is minimal. No data is created, modified, deleted, or sent externally.
From the tool's definition Tool retrieves the plain-text body of a sandbox message using 'get-' prefix and 'retrieve' semantics; no modification, deletion, or external side effects.
Attacks that exploit this kind of access
Get the plain-text body of a sandbox message. It is categorised as a Read tool in the Mcp Mailtrap MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mailtrap MCP server in PolicyLayer and add a rule for get-sandbox-message-text: 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.
get-sandbox-message-text 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 get-sandbox-message-text 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 get-sandbox-message-text. 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.
get-sandbox-message-text 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 →