AI agents use send_email to create or update resources in Zoho Mail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zoho Mail environment.
This tool creates new email messages and dispatches them, which is a reversible modification of data (emails can be unsent or recalled in some systems, though typically only within a short window). It does not execute arbitrary code, delete data, or move money.
From the tool's definition Tool description states 'Send an email from the configured ZOHO_SENDER address' — the verb 'send' and the direct action of composing and transmitting email messages indicate a Write operation that creates new messages.
Attacks that exploit this kind of access
Send an email from the configured ZOHO_SENDER address. It is categorised as a Write tool in the Zoho Mail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zoho Mail MCP server in PolicyLayer and add a rule for send_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 Zoho Mail. Nothing to install.
send_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_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_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_email is provided by the Zoho Mail MCP server (sirgreed808/zoho-mail-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 →