中文 AI 文本去 AI 腔改写:5 档强度,只改句子不改事实,网页 / API / MCP 三入口
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
查这个密钥今天还剩多少次、多少字。
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http ka-forge https://ai.ctaning.cn/mcp
查这个密钥今天还剩多少次、多少字。
No arguments.
{
"type": "object",
"properties": {}
}把一段中文改写成更自然、更像人写的版本(去 AI 腔)。返回改写后的正文。
| Argument | Type | Description |
|---|---|---|
| text* | string | 要改写的原文,至少 10 字 |
| level | integer | 改写强度:1 润色、2 轻改、3 中度、4 深度、5 重写。默认 1 |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "要改写的原文,至少 10 字"
},
"level": {
"type": "integer",
"maximum": 5,
"minimum": 1,
"description": "改写强度:1 润色、2 轻改、3 中度、4 深度、5 重写。默认 1"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.