# gmail_send_message

Send a Gmail message.

Agent View of the PolicyLayer registry record for `gmail_send_message`. HTML page: https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-send-message

## Facts

- Tool: `gmail_send_message`
- Server: Gmail MCP Server (`ampcome-mcps/gmail-mcp`) — https://policylayer.com/tools/ampcome-mcps-gmail-mcp.md
- Homepage: https://github.com/ampcome-mcps/gmail-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "gmail_send_message",
    "arguments": {}
  }
}
```

## Why gmail_send_message is rated Medium

Sending emails creates new data and commits communication on behalf of the user. While reversible (messages can be deleted), this is a Write operation with high severity due to potential for phishing, spam, credential leakage, or impersonation if misused by an AI agent. Not Financial (no money involved), not Destructive (emails can be deleted), not Execute (it sends, not runs code with variable side effects).

From the tool's own definition: "Tool name 'gmail_send_message' and description 'Send a Gmail message' indicate creation of new email messages. Server description confirms 'sending' emails is a core capability."

## Use case

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

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Gmail MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "gmail_send_message": {
      "limits": [
        {
          "counter": "gmail_send_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Gmail MCP Server (7)

- `gmail_delete_messages` — Destructive — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-delete-messages.md
- `gmail_get_message` — Read — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-get-message.md
- `gmail_get_stats` — Read — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-get-stats.md
- `gmail_list_messages` — Read — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-list-messages.md
- `gmail_search_messages` — Read — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-search-messages.md
- `gmail_mark_as_read` — Write — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-mark-as-read.md
- `gmail_send_message_with_attachment` — Write — https://policylayer.com/tools/ampcome-mcps-gmail-mcp/gmail-send-message-with-attachment.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=ampcome-mcps-gmail-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ampcome-mcps-gmail-mcp