AI agents use send_email_tool 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 emails is a Write operation—it creates and transmits data (email messages). However, it rates high severity because email can be used for unauthorized communication, phishing, spam, credential harvesting, or impersonation if an AI agent misuses it without proper authorization checks. The blast radius is significant as emails reach external recipients and can damage reputation or violate compliance.
From the tool's definition Tool name is 'send_email_tool' and server description explicitly states it 'enables LLMs to compose and send emails with attachments.' The tool description is empty, but the server-level documentation clearly indicates this tool sends emails.
Documented attack patterns abuse exactly the kind of access send_email_tool 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_tool:
{
"version": "1",
"default": "deny",
"tools": {
"send_email_tool": {
"limits": [
{
"counter": "send_email_tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_email_tool 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_tool. 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_tool: 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_tool 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_tool 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_tool. 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_tool 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.