Rephrasy

io.github.rephrasyai由 GitHub 账号 rephrasyai 发布v0.1.0更新于 Oct 24, 2026

Humanize AI text and check AI-detection scores from Claude, Cursor, or any MCP client.

概览

AI 生成的概览

让助手把 AI 生成的文本改写得更像人写,并评估文本被判定为 AI 写作的可能性。

可以做什么
该服务器提供两个工具。humanize 工具在保留原意的前提下,把 AI 生成的文本改写为自然、像人写的风格,并返回改写后的文本和计费字数。detect 工具评估文本被判定为 AI 写作的可能性,返回总体分数,并可选返回逐句分数。两个工具都通过 Rephrasy API,在 Claude、Cursor 等 MCP 客户端中调用。
适用场景
适合需要让文本读起来像人写的起草或编辑场景,也适合在发布前检查草稿的 AI 检测分数。它适合在编辑器或智能体工作流中,把改写与验证放在同一次会话里完成。
运行要求
需要本地 Node.js 运行环境,以 stdio 方式运行 npm 包 @rephrasy/mcp;还需要通过环境变量 REPHRASY_API_KEY 提供 Rephrasy API 密钥,密钥来自 Rephrasy 账户(Account 下的 API)。需要能访问 Rephrasy 服务的网络连接。
安装前请注意
REPHRASY_API_KEY 密钥会写入客户端配置,应避免放入共享文件。两个工具都会按你的 Rephrasy 套餐计费,humanize 会返回计费字数,因此使用会产生费用。提交给工具的文本会发送到 Rephrasy 服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Rephrasy,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Rephrasy MCP Server

[npm]

Use Rephrasy from Claude, Cursor, or any MCP client: humanize AI-generated text and images, and check AI-detection scores, without leaving your editor or agent workflow.

Four tools, one API key:

ToolWhat it does
humanizeRewrites AI-generated text in a natural, human style while preserving meaning
detectScores how likely a text is to be flagged as AI-written (overall + optional per-sentence)
humanize_imageHumanizes a local or remote image and saves the result next to the original
get_image_resultCollects an image that was still processing (free)

Setup

1. Get an API key — sign in at rephrasy.ai → Account → API. Both tools bill against your Rephrasy plan.

2. Add the server to your client:

Claude Code

bash
claude mcp add rephrasy -e REPHRASY_API_KEY=<your-key> -- npx -y @rephrasy/mcp

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

json
{  "mcpServers": {    "rephrasy": {      "command": "npx",      "args": ["-y", "@rephrasy/mcp"],      "env": { "REPHRASY_API_KEY": "<your-key>" }    }  }}

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

json
{  "mcpServers": {    "rephrasy": {      "command": "npx",      "args": ["-y", "@rephrasy/mcp"],      "env": { "REPHRASY_API_KEY": "<your-key>" }    }  }}

Until the package is on npm you can run it straight from GitHub: replace "args": ["-y", "@rephrasy/mcp"] with "args": ["-y", "github:rephrasyai/rephrasy-mcp"].

Hosted server (no install)

Rephrasy also runs a hosted MCP server, so clients that speak streamable HTTP need nothing installed locally:

bash
claude mcp add rephrasy https://v2-humanizer.rephrasy.ai/mcp -t http \  -H "Authorization: Bearer <your-key>"

It supports OAuth as well — ChatGPT and other clients that require it discover it from the server and send you through a one-time consent page, so the key never reaches the client. The hosted server carries a wider tool set (engine recommendations, readability, bring-your-own-key detectors). Full docs: https://rephrasy.ai/mcp.

Tools

humanize

ParameterTypeRequiredDescription
textstringyesThe text to humanize
modelstringnoRephrasy model, default "v4" (recommended). See Models
languagestringnoOutput language hint (e.g. "en", "de"); defaults to input language

Returns the rewritten text plus the number of words charged.

Models
modelWhen to use it
v4Default and recommended. Natural rhythm and sentence variety, length close to the source.
superstealthNewest. Built for the highest bypass rates, recommended against Pangram. Slower: 10–60 s per request.
ft_clean-v3Highest meaning retention and near-identical length — technical writing and anything with figures.
Undetectable ModelBest against academic detectors.
SEO ModelSimple, informal phrasing built around keywords.
<writing style id>Rewrites in one of your saved Writing Styles.

v3 and Undetectable Model v2 are retired. Old calls keep working: the API routes v3 to superstealth and v2 to v4. The v3-only style parameter is gone.

detect

ParameterTypeRequiredDescription
textstringyesThe text to score (max 15,000 characters)
per_sentencebooleannoIf true, also returns a score per sentence

Returns JSON with scores.overall (lower = more human-like) and, in per-sentence mode, sentences.

humanize_image

ParameterTypeRequiredDescription
pathstringone ofLocal image file (PNG, JPEG or WEBP, max 4 MB)
urlstringone ofOr an http(s) link to the image
qualitystringno"standard" (default, usually under a minute) or "hq" (about 4 minutes)
output_pathstringnoWhere to save the result; defaults to <name>-humanized.<ext> next to the input

A diffusion pass removes invisible AI watermarks such as SynthID while subject, composition and resolution stay the same. Costs 10 credits on standard and 20 on hq; a failed image is refunded. Standard images are usually saved within the call. If a job is still running, the tool returns a job_id instead.

get_image_result

ParameterTypeRequiredDescription
job_idstringyesThe job_id from humanize_image
output_pathstringnoWhere to save the result

Waits up to about 50 seconds per call and saves the image once it is done. Results stay available for 72 hours and also show up in your image history on rephrasy.ai.

Example prompts

  • "Humanize this paragraph, then run detect on the result to verify it."
  • "Humanize this essay with superstealth so it passes Pangram."
  • "Rewrite my draft with the humanize tool using model <style-id> (my writing style)."
  • "Check which sentences of this post read as AI-written."
  • "Humanize ~/Desktop/hero.png in hq and tell me where you saved it."

Development

bash
npm installnpm run buildREPHRASY_API_KEY=<key> node dist/index.js   # runs on stdio

License

MIT © Rephrasy

来源:README.md,提交 579032c

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分