email_send · UnClick MCP: Risk & Policy

WHAT IT DOES

What email_send does on UnClick

AI agents use email_send to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.

PARAMETERS

Parameter	Type	Required
`cc`	string	—
`to`	string	Yes
`bcc`	string	—
`body`	string	Yes
`email`	string	—
`subject`	string	Yes
`password`	string	—

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why email_send needs a policy

Sending email is a Write action that modifies external state (adds message to mailbox/inbox) but is reversible (email can be deleted or unsent in most cases). It is not Destructive (emails are not permanently irreversible upon send in most systems), not Financial (no money moves), not Execute (no arbitrary code/command execution).

From the tool's definition Tool name is 'email_send' and description states 'Send an email via Gmail/IMAP' — this creates/sends a new message, a reversible write operation.

Risk signalsHandles credentials or secrets (password) · Accepts raw HTML/template content (body)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

email_send Rate-limited

email_send 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "email_send": {
      "limits": [
        {
          "counter": "email_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches UnClick, so you can run agents against it safely.

FAQ

Questions about email_send

What does the email_send tool do? +

Send an email via Gmail/IMAP. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does email_send accept? +

email_send accepts 7 parameters: cc, to, bcc, body, email, subject, password. Required: to, body, subject. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on email_send? +

Register the UnClick MCP server in PolicyLayer and add a rule for email_send: 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 UnClick. Nothing to install.

What risk level is email_send? +

email_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit email_send? +

Yes. Add a rate_limit block to the email_send 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.

How do I block email_send completely? +

Set action: deny in the PolicyLayer policy for email_send. 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.

What MCP server provides email_send? +

email_send is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.