AI agents call get_send_status to retrieve information from Email without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about an email send operation without modifying any data or triggering new actions. It is purely informational, similar to checking the result of an already-completed operation. The narrow scope (checking approval status) and read-only nature classify it as Read with low severity.
From the tool's definition Tool name 'get_send_status' and description indicate it retrieves the status of a previously sent email ('outcome of a send'). No modification, deletion, or execution occurs—it queries the state of an existing send operation.
Attacks that exploit this kind of access
The outcome of a send that returned pending_approval: status is pending,. It is categorised as a Read tool in the Email MCP Server, which means it retrieves data without modifying state.
Register the Email MCP server in PolicyLayer and add a rule for get_send_status: 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 Email. Nothing to install.
get_send_status 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_send_status 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_send_status. 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_send_status is provided by the Email MCP server (swapnilsurdi/email_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 →