# humanizer-ru

Detects AI patterns and boilerplate in Russian text. It helps agents perform targeted stylistic editing without rewriting the underlying message.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 489
- Author: ilyautov
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ilyautov/humanizer-ru
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/humanizer-ru

## What it does

This server equips models with an editing pipeline for Russian prose. Its engine checks against 67 synthetic patterns across 16 categories, along with 21 strict phrasal bans. The tool flags issues and assigns a cleanliness score from 0 to 100.

Execution requires uv in your environment. It applies targeted fixes to specific fragments instead of regenerating the entire paragraph. The fact-checking logic checks extracted entities, so you must still verify reasoning manually.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add humanizer-ru -- uvx ru-humanizer
```
uvx runs the command named after the package; if the README names another one, use uvx --from ru-humanizer <command>

### Codex

**Platform CLI**
```bash
codex mcp add humanizer-ru -- uvx ru-humanizer
```
uvx runs the command named after the package; if the README names another one, use uvx --from ru-humanizer <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "humanizer-ru": {
            "command": "uvx",
            "args": [
                "ru-humanizer"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ru-humanizer <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "humanizer-ru": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "ru-humanizer"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ru-humanizer <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add humanizer-ru uvx ru-humanizer
```
uvx runs the command named after the package; if the README names another one, use uvx --from ru-humanizer <command>

## When to use it
- spot AI writing markers in Russian drafts
- score text cleanliness from 0 to 100
- remove rigid cliches without changing facts
- apply targeted edits to flagged sections

## Example prompts
- Audit this Russian draft using humanizer-ru and show all markers
- Edit the text to remove Russian AI cliches while keeping all facts
- Scan this draft and calculate its cleanliness score

## Similar
- [Reactive Resume](https://affpapa.org/en/nevibecode/mcp/reactive-resume.md) — MCP server · ★ 44874
- [Sui Knowledge Base (kapa.ai)](https://affpapa.org/en/nevibecode/mcp/sui-knowledge-base-kapaai.md) — MCP server · ★ 7784
- [Claude Code Ultimate Guide](https://affpapa.org/en/nevibecode/mcp/claude-code-ultimate-guide.md) — MCP server · ★ 6237
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5548
- [RevoGrid DataGrid MCP Pro](https://affpapa.org/en/nevibecode/mcp/revogrid-datagrid-mcp-pro.md) — MCP server · ★ 3450
- [Claude Code Explorer MCP](https://affpapa.org/en/nevibecode/mcp/codeaashu-claude-code-explorer-mcp.md) — MCP server · ★ 3409

From the same set: [ilyautov/humanizer-ru](https://affpapa.org/en/nevibecode/by/ilyautov/humanizer-ru.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md