
Rephrasy
io.github.rephrasyai由 GitHub 帳號 rephrasyai 發布v0.1.0更新於 Oct 24, 2026
Humanize AI text and check AI-detection scores from Claude, Cursor, or any MCP client.
概覽
讓助理把 AI 生成的文字改寫得更像真人撰寫,並評估文字被判定為 AI 撰寫的可能性。
- 可以做什麼
- 此伺服器提供兩個工具。humanize 工具在保留原意的情況下,把 AI 生成的文字改寫成自然、像真人撰寫的風格,並回傳改寫後的文字與計費字數。detect 工具評估文字被判定為 AI 撰寫的可能性,回傳整體分數,並可選擇回傳逐句分數。兩個工具都透過 Rephrasy API,在 Claude、Cursor 等 MCP 用戶端中呼叫。
- 適用情境
- 適合需要讓文字讀起來像真人撰寫的起草或編輯情境,也適合在發布前檢查草稿的 AI 檢測分數。它適合在編輯器或代理工作流程中,把改寫與驗證放在同一次工作階段完成。
- 執行需求
- 需要本機 Node.js 執行環境,以 stdio 方式執行 npm 套件 @rephrasy/mcp;還需要透過環境變數 REPHRASY_API_KEY 提供 Rephrasy API 金鑰,金鑰來自 Rephrasy 帳戶(Account 下的 API)。需要能連線至 Rephrasy 服務的網路。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Rephrasy,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Rephrasy MCP Server
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:
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
Claude Desktop
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
Cursor
Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
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:
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
Returns the rewritten text plus the number of words charged.
Models
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
Returns JSON with scores.overall (lower = more human-like) and, in per-sentence mode, sentences.
humanize_image
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
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
License
MIT © Rephrasy
來源:README.md,提交 579032c
工具
0版本歷史
1- v0.1.0最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分