This record as markdown: /tools/lxwl-mcp-server/onloon-normal-mail--sendmessage.md
What onloon-normal-mail__sendMessage does on Lxwl
AI agents use onloon-normal-mail__sendMessage to create or update resources in Lxwl, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lxwl environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
cc | object | — | 邮箱。字符串、逗号/分号分隔，或 [{mail,name,personId}] |
to | string | — | 邮箱。字符串、逗号/分号分隔，或 [{mail,name,personId}] |
bcc | object | — | 邮箱。字符串、逗号/分号分隔，或 [{mail,name,personId}] |
body | string | — | 正文。字符串当 HTML；或 {html} / {text} |
from | string | — | |
text | object | — | 正文。字符串当 HTML；或 {html} / {text} |
dryRun | boolean | — | |
sender | string | — | from 别名 |
attachs | string | — | formatMailAttachments 输出的 JSON 字符串，与 attachments 二选一 |
draftId | string | — | |
subject | string | — | |
priority | integer | — |
Parameters from the server's own tool schema.
Why onloon-normal-mail__sendMessage is rated Medium
An AI agent can call onloon-normal-mail__sendMessage faster than any human can review: one bad instruction and it creates or modifies resources in Lxwl by the hundred, each call as confident as the last.
Risk signalsAccepts file system path (attachments[].fileName) · Accepts raw HTML/template content (body) · High parameter count (29 properties)
Attacks that exploit this kind of access
The rule that runs onloon-normal-mail__sendMessage safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Lxwl, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For onloon-normal-mail__sendMessage, this is the rule to start with:
onloon-normal-mail__sendMessage 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 Lxwl, apply this rule, and every onloon-normal-mail__sendMessage call is checked against it from then on.
Questions about onloon-normal-mail__sendMessage
发送新邮件（高风险，须 confirmed=true）. It is categorised as a Write tool in the Lxwl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
onloon-normal-mail__sendMessage accepts 12 parameters: cc, to, bcc, body, from, text, dryRun, sender, attachs, draftId, subject, priority. The full parameter table on this page comes from the server's own tool schema.
Register the Lxwl MCP server in PolicyLayer and add a rule for onloon-normal-mail__sendMessage: 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 Lxwl. Nothing to install.
onloon-normal-mail__sendMessage 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 onloon-normal-mail__sendMessage 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 onloon-normal-mail__sendMessage. 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.
onloon-normal-mail__sendMessage is provided by the Lxwl MCP server (@lxwl/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Lxwl, and thousands of servers like it.
This server
Across the catalogue