This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/gmail-send.md
What gmail_send does on UnClick
AI agents use gmail_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.
| Parameter | Type | Required | Description |
|---|---|---|---|
to | string | Yes | Recipient email address |
body | string | Yes | Plain-text email body |
from | string | — | Optional From header (defaults to me) |
subject | string | Yes | Email subject |
access_token | string | — | Gmail access token |
Parameters from the server's own tool schema.
Why gmail_send is rated Medium
This tool creates and sends email messages, which is a Write operation—it modifies state (creates new messages in recipient inboxes) reversibly (messages can be deleted). However, severity is high rather than medium because sending emails can have significant consequences: it could be used to impersonate users, send spam, phishing attacks, or unwanted communications at scale.
From the tool's definition Tool name 'gmail_send' and description 'Send a plain-text Gmail message' explicitly indicate creation and transmission of email messages.
Risk signalsHandles credentials or secrets (access_token) · Accepts raw HTML/template content (body)
Attacks that exploit this kind of access
The rule that runs gmail_send safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gmail_send, this is the rule to start with:
gmail_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.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every gmail_send call is checked against it from then on.
Questions about gmail_send
Send a plain-text Gmail message. 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.
gmail_send accepts 5 parameters: to, body, from, subject, access_token. Required: to, body, subject. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for gmail_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.
gmail_send 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 gmail_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.
Set action: deny in the PolicyLayer policy for gmail_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.
gmail_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.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue