Send a system email message to an agent.
AI agents use sendSystemEmailToAgent to create or update resources in Lofty MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lofty MCP Server environment.
This tool creates a new email artifact (reversible action—emails can be recalled or deleted in most systems) and sends it to an agent. It does not execute arbitrary code, delete data irreversibly, move money, or perform read-only retrieval.
From the tool's definition Tool name 'sendSystemEmailToAgent' and description 'Send a system email message to an agent' indicate the tool composes and dispatches an email message, which creates a new communication record.
Attacks that exploit this kind of access
Send a system email message to an agent. It is categorised as a Write tool in the Lofty MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lofty MCP Server MCP server in PolicyLayer and add a rule for sendSystemEmailToAgent: 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 Lofty MCP Server. Nothing to install.
sendSystemEmailToAgent 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 sendSystemEmailToAgent 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 sendSystemEmailToAgent. 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.
sendSystemEmailToAgent is provided by the Lofty MCP Server MCP server (nerdsnipe-inc/lofty-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 →