AI agents use send_email to create or update resources in MCP Email Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Email Server environment.
Sending email is a write operation that creates and modifies (transmits) data, but is reversible in nature—emails can be recalled, marked as spam, or deleted after sending. It does not permanently destroy data or move money, so it does not qualify as Destructive or Financial.
From the tool's definition Tool name is 'send_email' within an 'MCP Email Server' that 'enables LLMs to compose and send emails with attachments.' The server description explicitly states the capability to 'compose and send emails,' confirming this tool creates and transmits new…
Documented attack patterns abuse exactly the kind of access send_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Email Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_email:
{
"version": "1",
"default": "deny",
"tools": {
"send_email": {
"limits": [
{
"counter": "send_email_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_email stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
send_email. It is categorised as a Write tool in the MCP Email Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Email Server 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 MCP Email Server. 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 MCP Email Server MCP server (shy2593666979/mcp-server-email). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP Email Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP Email Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.