{
  "markdown": "# Rephrasy MCP Server\n\n[![npm](https://img.shields.io/npm/v/@rephrasy/mcp)](https://www.npmjs.com/package/@rephrasy/mcp)\n\nUse [Rephrasy](https://rephrasy.ai) from Claude, Cursor, or any MCP client: humanize AI-generated text and check AI-detection scores without leaving your editor or agent workflow.\n\nTwo tools, one API key:\n\n| Tool | What it does |\n|---|---|\n| `humanize` | Rewrites AI-generated text in a natural, human style while preserving meaning |\n| `detect` | Scores how likely a text is to be flagged as AI-written (overall + optional per-sentence) |\n\n## Setup\n\n**1. Get an API key** — sign in at [rephrasy.ai](https://rephrasy.ai) → Account → API. Both tools bill against your Rephrasy plan.\n\n**2. Add the server to your client:**\n\n### Claude Code\n\n```bash\nclaude mcp add rephrasy -e REPHRASY_API_KEY=<your-key> -- npx -y @rephrasy/mcp\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json` (Settings → Developer → Edit Config):\n\n```json\n{\n  \"mcpServers\": {\n    \"rephrasy\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@rephrasy/mcp\"],\n      \"env\": { \"REPHRASY_API_KEY\": \"<your-key>\" }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"rephrasy\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@rephrasy/mcp\"],\n      \"env\": { \"REPHRASY_API_KEY\": \"<your-key>\" }\n    }\n  }\n}\n```\n\n> 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\"]`.\n\n## Tools\n\n### `humanize`\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `text` | string | yes | The text to humanize |\n| `model` | string | no | Rephrasy model, default `\"v3\"` |\n| `style` | string | no | Writing-style ID from your account to mimic a specific voice |\n| `language` | string | no | Output language hint (e.g. `\"en\"`, `\"de\"`); defaults to input language |\n\nReturns the rewritten text plus the number of words charged.\n\n### `detect`\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `text` | string | yes | The text to score (max 15,000 characters) |\n| `per_sentence` | boolean | no | If `true`, also returns a score per sentence |\n\nReturns JSON with `scores.overall` (lower = more human-like) and, in per-sentence mode, `sentences`.\n\n## Example prompts\n\n- *\"Humanize this paragraph, then run detect on the result to verify it.\"*\n- *\"Rewrite my draft with the humanize tool using my writing style `<style-id>`.\"*\n- *\"Check which sentences of this post read as AI-written.\"*\n\n## Development\n\n```bash\nnpm install\nnpm run build\nREPHRASY_API_KEY=<key> node dist/index.js   # runs on stdio\n```\n\n## License\n\nMIT © Rephrasy\n",
  "bytes": 2716,
  "sha": "6af87c57d0ae0e1ccbac269b037b8791d433cb7b03b12b616c0f3ad4f62264e3",
  "repo_slug": "rephrasyai/rephrasy-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_rephrasyai_rephrasy_mcp_e7c1f400/readme"
}