Humantextpro

io.github.humantextproPublished by GitHub account humantextprov1.0.3Updated Oct 27, 2026

AI text detection and humanization for Claude Code, Cursor, and Windsurf.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Detects AI-generated text and rewrites it to sound human, with optional verification, using humantext.pro credits from inside an MCP client.

What you can do
  • Analyze text for AI-generated content and get a score and verdict
  • Rewrite AI-sounding text with selectable tone, style and rewrite level
  • Humanize text and then re-check the result with detection in one step
  • Check the account's remaining credits and plan details
When to use it
Useful when you draft or edit prose in an editor-based assistant and want a quick AI-detection score or a more natural-sounding rewrite without leaving the client. Also handy for confirming that a humanized passage passes detection.
Requirements
Runs locally via npx from the npm package @humantext/mcp-server, so Node.js is needed. Requires a humantext.pro account and an API key supplied in the HUMANTEXT_API_KEY environment variable; an optional HUMANTEXT_BASE_URL can point at a custom API endpoint. Network access to the humantext.pro API is required.
Before you install
The API key is a paid-account credential stored in the client config, so keep that file out of version control. Every detection and humanization call consumes subscription credits based on word count, and plans are billed monthly. Text you submit is sent to the humantext.pro service for processing.

Installation

In SourceWeft

  1. Open Humantextpro in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

humantext.pro MCP Server

AI text detection and humanization tools for Claude Code, Cursor, Windsurf, and any MCP-compatible client.

Check if text sounds AI-generated and transform it to read naturally — without leaving your editor.

Quick Start

1. Get your API key

Sign up at humantext.pro and generate an API key on your API page.

2. Add to your MCP client

Claude Code / VS Code:

Add to .claude/mcp.json in your project (or global settings):

json
{  "mcpServers": {    "humantext": {      "command": "npx",      "args": ["-y", "@humantext/mcp-server"],      "env": {        "HUMANTEXT_API_KEY": "your_api_key_here"      }    }  }}

Cursor:

Add to .cursor/mcp.json in your project:

json
{  "mcpServers": {    "humantext": {      "command": "npx",      "args": ["-y", "@humantext/mcp-server"],      "env": {        "HUMANTEXT_API_KEY": "your_api_key_here"      }    }  }}

Claude Desktop:

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "humantext": {      "command": "npx",      "args": ["-y", "@humantext/mcp-server"],      "env": {        "HUMANTEXT_API_KEY": "your_api_key_here"      }    }  }}

3. Use it

Ask your AI assistant:

  • "Check if this text sounds AI-generated"
  • "Humanize this paragraph to sound more natural"
  • "Humanize this text and verify the result passes AI detection"
  • "What's my humantext.pro credit balance?"

Tools

detect_ai

Analyze text for AI-generated content. Returns a score (0-100%) and verdict.

ParameterTypeRequiredDescription
textstringYesText to analyze (min 50 characters)

Example output:

AI Detection Result━━━━━━━━━━━━━━━━━━━Score: 87% AIVerdict: AI GeneratedWords analyzed: 156Credits remaining: 4,844

humanize_text

Transform AI-generated text to sound natural and human-written.

ParameterTypeRequiredDescription
textstringYesText to humanize (min 50 characters)
toneenumNocasual, standard, academic, professional, marketing
styleenumNogeneral, essay, article, marketing, creative, formal, report, business, legal
levelenumNolight, balanced, aggressive (default: aggressive)

humanize_and_detect

Two-step process: humanize text, then verify the result with AI detection. Proves the output passes detection.

Same parameters as humanize_text.

Example output:

Humanized & Verified━━━━━━━━━━━━━━━━━━━━
[humanized text here]
━━━━━━━━━━━━━━━━━━━━Verification: 12% AI → Mostly HumanWords: 156 | Credits remaining: 4,532

check_balance

Check your account balance and plan details. No parameters required.

Pricing

The MCP server uses your humantext.pro subscription credits:

PlanPriceMonthly Credits
Basic$7.99/mo5,000 words
Pro$19.99/mo15,000 words
Ultra$39.99/mo30,000 words

Both detection and humanization consume credits based on input word count.

Environment Variables

VariableRequiredDescription
HUMANTEXT_API_KEYYesAPI key from humantext.pro/api
HUMANTEXT_BASE_URLNoCustom API URL (default: https://humantext.pro/api/v1)

Links

License

MIT

Source: README.md at commit 925a6bf

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts