Rephrasy MCP server
io.github.rephrasyai/rephrasy-mcp·v0.1.0Humanize AI text and check AI-detection scores from Claude, Cursor, or any MCP client.
0 stars28 downloads/wk
Reviews
Write oneNobody has reviewed Rephrasy yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Rephrasy tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
detectScore a text with Rephrasy's AI detector. Returns an overall AI-likelihood score
humanizeRewrite AI-generated text with Rephrasy so it reads in a natural, human style —
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 54 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Rephrasy compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 28
- more than 15% of 12,191 servers with a package
What its tools let an agent do: 2 read
Install Rephrasy in Claude Code, Cursor or VS Code
Runs npx -y @rephrasy/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add rephrasy-mcp -- npx -y @rephrasy/mcp
What the publisher says
From the Rephrasy repository's README, as published. We do not edit it. Read it on GitHub
Rephrasy MCP Server
Use Rephrasy from Claude, Cursor, or any MCP client: humanize AI-generated text and check AI-detection scores without leaving your editor or agent workflow.
Two 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 mcp add rephrasy -e REPHRASY_API_KEY=<your-key> -- npx -y @rephrasy/mcpClaude Desktop
Add to claudedesktopconfig.json (Settings → Developer → Edit Config):
{
"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):
{
"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"].
Tools
humanize
Returns the rewritten text plus the number of words charged.
detect
Returns JSON with scores.overall (lower = more human-like) and, in per-sentence mode, sentences.
Example prompts
- "Humanize this paragraph, then run detect on the result to verify it."
- "Rewrite my draft with the humanize tool using my writing style ."
- "Check which sentences of this post read as AI-written."
Development
npm install
npm run build
REPHRASY_API_KEY=<key> node dist/index.js # runs on stdioLicense
MIT © Rephrasy
Nothing above is checked by us. What we check is on the safety report.
Rephrasy: common questions
- Is Rephrasy MCP server safe?
- Mostly: it is graded B (78/100). Read the Rephrasy safety report
- How do I install Rephrasy?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Rephrasy need an API key?
- Yes. The registry entry asks for
REPHRASY_API_KEY. - Is Rephrasy maintained?
- The last commit was 95 days ago (2026-08-01). The latest release is v0.1.0.
- How does Rephrasy compare with other MCP servers?
- safety score 78/100 (higher than 57% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.