What is humanizer-mcp CLAUDE.md?

Project instructions for a writing server that supplies rules and examples for making text sound more naturally human. The server uses an AI coding-agent connection and stores its reference material in tracked JSON files.

Helping an AI coding agent consult the project's writing rules and reference documents while developing, changing, deploying, or debugging the humanizer server.

The information provided describes the project's documentation and operating setup, but does not specify a user-facing writing workflow beyond supplying writing and revision guidance.

How nicojan/humanizer-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nicojan/humanizer-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nicojan/humanizer-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nicojan/humanizer-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nicojan/humanizer-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nicojan/humanizer-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nicojan/humanizer-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nicojan/humanizer-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nicojan/humanizer-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nicojan/humanizer-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,579 This file is loaded in full into every session.

When invoked 9,579 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.09579	$0.09579
Opus 5.5	$0.03832	$0.03832
Sonnet 5.5	$0.01916	$0.01916
Haiku 4.5	$0.00958	$0.00958

Measured 1mo ago against content hash 75ae693d77e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

humanizer-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-humanizer

An MCP server that provides psycholinguistic, lexical, structural, and discourse-level rules for producing naturally human-sounding written content. It serves as a reference for Claude during writing and revision tasks: the server supplies rules and examples, and Claude applies them.

Server name: humanizer_mcp (Python convention: {service}_mcp) All tool names prefixed with humanizer_ to avoid conflicts with other MCP servers.

Reference Docs

File	Load When
`docs/PRD.md`	Understanding what this server does and its role in the ecosystem
`docs/DATA_SCHEMA.md`	Modifying data file structure or adding new data files
`docs/API_SPEC.md`	Adding or modifying tools: parameter specs, validation, error handling
`docs/DEPLOYMENT.md`	Deploying, redeploying, or debugging infrastructure

Tech Stack

Parameter	Value
Language	Python
Framework	FastMCP (`mcp` package)
Storage	JSON files in Git-tracked `/data` directory
Transport	Streamable HTTP
Auth	None (public, read-only)
Container	Docker + docker-compose.yml
Host	Any container host; single stateless container behind a reverse proxy or tunnel
Port	8016 (configurable via `PORT`)
PUID/PGID	`1026` / `100`
TZ	`America/Vancouver`

See docs/DEPLOYMENT.md for deployment and configuration.

Project Structure

mcp-humanizer/
├── CLAUDE.md
├── docs/
│   ├── PRD.md
│   ├── DATA_SCHEMA.md
│   ├── API_SPEC.md
│   └── DEPLOYMENT.md
├── src/
│   ├── __init__.py
│   ├── server.py
│   ├── middleware.py
│   ├── tools/
│   │   ├── __init__.py
│   │   ├── read.py
│   │   └── check.py
│   ├── checker/
│   │   ├── __init__.py
│   │   ├── emdash.py
│   │   ├── punctuation.py
│   │   ├── phrases.py
│   │   ├── insistence.py
│   │   ├── structures.py
│   │   ├── segment.py
│   │   ├── metrics.py
│   │   ├── budgets.py
│   │   ├── loader.py
│   │   ├── inflect.py
│   │   ├── report.py
│   │   └── util.py
│   └── storage/
│       ├── __init__.py
│       └── json_store.py
├── data/
│   ├── foundation.json
│   ├── lexical_patterns.json
│   ├── structural_patterns.json
│   ├── sentiment_tone.json
│   ├── discourse_cohesion.json
│   ├── psycholinguistic_texture.json
│   ├── content_profiles.json
│   ├── anti_patterns.json
│   ├── banned_structures.json
│   ├── caveats.json
│   └── self_review.json
├── Dockerfile
├── docker-compose.yml
├── requirements.txt
├── requirements.lock
├── .gitignore
└── README.md

Read the full file on GitHub · 130 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +11 lines · +3,390 tokens per session 75ae693d77e1
2mo ago First seen · 119 lines · 6,189 tokens per session scan A 36b121b504a9

Subscribe to this mod's changes

humanizer-mcp CLAUDE.md is an instructions file published in the GitHub repository nicojan/humanizer-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 9,579 tokens to every session, about $0.0383 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

LLM Python Writing and docs ai-writing mcp mcp-server nlp

humanizer-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
humanizer-mcp CLAUDE.mdnicojan/humanizer-mcp	Instructions file	0	7d ago	MIT	A	9,579	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

humanizer-mcp: Instructions file for Claude Code