How do I let an AI agent google workspace gmail send email?

Connect Google Workspace to CybrLink, then expose the `google_workspace_gmail_send_email` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Google Workspace credential server-side and runs one scoped API call. Send a plain-text email from the connected Google Workspace Gmail account. Returns { id, threadId, labelIds }.

Does the AI model see my Google Workspace credentials when using GOOGLE_WORKSPACE_GMAIL_SEND_EMAIL?

No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can take this action in Google Workspace without the OAuth token or API key ever entering its context.

Google Workspace · Email

`GOOGLE_WORKSPACE_GMAIL_SEND_EMAIL`

Send a plain-text email from the connected Google Workspace Gmail account. Returns { id, threadId, labelIds }.

Provider: Google Workspace
Access: Write
Category: Email
Version: v1

Input schema

{
  "type": "object",
  "properties": {
    "to": {
      "type": "string",
      "description": "Recipient email address."
    },
    "cc": {
      "type": "string",
      "description": "Optional CC recipient list."
    },
    "bcc": {
      "type": "string",
      "description": "Optional BCC recipient list."
    },
    "subject": {
      "type": "string",
      "description": "Email subject."
    },
    "body": {
      "type": "string",
      "description": "Plain-text email body."
    }
  },
  "required": [
    "to",
    "subject",
    "body"
  ],
  "additionalProperties": false
}

How to call it

Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls google_workspace_gmail_send_email with arguments matching the schema above.

CybrLink validates the input, injects the connected Google Workspace credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.

Write action — gate behind explicit user approval and write scope.

Frequently asked

How do I let an AI agent google workspace gmail send email?: Connect Google Workspace to CybrLink, then expose the `google_workspace_gmail_send_email` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Google Workspace credential server-side and runs one scoped API call. Send a plain-text email from the connected Google Workspace Gmail account. Returns { id, threadId, labelIds }.
Does the AI model see my Google Workspace credentials when using GOOGLE_WORKSPACE_GMAIL_SEND_EMAIL?: No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can take this action in Google Workspace without the OAuth token or API key ever entering its context.

Connect Google Workspace All tools