humanizer
A powerful Model Context Protocol (MCP) server that helps refine AI-generated content to sound more natural and human-like. Built with advanced AI detection and text enhancement capabilities.
claude mcp add --transport stdio chongzixuan-ai-humanizer-mcp-server npx -y ai-humanizer-mcp-server \ --env CLAUDE_DESKTOP_CONFIG="Path to Claude Desktop developer config (optional)"
How to use
This MCP server, AI Humanize, refines AI-generated text to read as natural, human-like writing while preserving key terminology. It combines AI detection with text enhancement, grammar polishing, readability improvements, and length control to produce content that sounds authentic and clear. The server is designed to be integrated with Claude Desktop via MCP, enabling you to swap in a dedicated humanization capability alongside other MCP-powered tools. Use the provided commands to spin up the server through npx for quick trials or via a built-from-source setup if you prefer building locally from the repository. Once running, you can send text through Claude Desktop’s MCP interface and receive a refined version that maintains intended meaning and style while reducing robotic tone and awkward phrasing.
How to install
Prerequisites:
- Node.js version 16 or higher
- Claude Desktop (latest)
Option A: Run via npx (quick start)
- Ensure Claude Desktop is installed and open.
- Install and run the MCP server configuration via npx as described below:
Code snippet (npx):
# Configuration in Claude Desktop (Settings → Developer → Edit Config)
{
"mcpServers": {
"ai-humanizer": {
"command": "npx",
"args": ["-y", "ai-humanizer-mcp-server"]
}
}
}
- Restart Claude Desktop to apply changes.
Option B: Run from source code (build locally)
- Clone this repository.
- Install dependencies:
npm install
- Build the project:
npm run build
- Configure Claude Desktop to point to the built server:
{
"mcpServers": {
"ai-humanizer": {
"command": "node",
"args": ["<YOUR_PROJECT_PATH>/build/index.js"]
}
}
}
- Restart Claude Desktop to apply changes.
Additional notes
Tips and notes:
- The AI Humanizer aims to preserve domain-specific terminology and key phrases while improving tone, grammar, and readability.
- If you need to adjust output length, consider adding a length preference or prompt parameters in the underlying server configuration if supported.
- Ensure your Node.js version matches the prerequisites (>= 16) and that Claude Desktop is the latest version for compatibility with MCP integrations.
- When running via npx, an internet connection is required to fetch the package; for a production workflow, consider building from source and hosting the built index.js locally.
- If you encounter environment variable issues, try running with minimal env or explicitly define CLAUDE_DESKTOP_CONFIG to point to your Claude config file.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.