Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
io.github.manavmishra/zero-slop — MCP Server
This MCP server provides “Score and rewrite AI-assisted prose” while preserving names, numbers, quotes, links, and facts. It exposes 1 tool and is oriented toward editing and writing quality control via prose-linter and humanizer-style workflows. The project is MIT licensed and runtime dependencies are listed as 0.
🛠️ Key Features
Score AI-assisted prose
Rewrite prose while preserving: names, numbers, quotes, links, facts
1 available tool in this server
🚀 Use Cases
Editing AI-generated text without losing specific details (e.g., quotes and links)
Prose-linter style review for writing-assistant outputs
Humanizer workflows for improved readability
⚡ Developer Benefits
Stable execution with runtime dependencies: 0
Versioned release: 2.8.10
Topics include model-context-protocol and mcp-server for integration context
⚠️ Limitations
Server excerpt does not list additional tools beyond the total toolCount of 1
Functional scope is limited to scoring and rewriting with preservation guarantees
Edits pasted prose with server-side scoring and source-preservation checks. Cloudflare Workers AI handles hosted editing first. If it cannot return a usable edit, the service may send the draft and editing inputs through OpenRouter to a free model provider that may keep the draft and the edit or use them to train models. Returns edited or unchanged text, writing scores, completed checks, and any review warnings.
Parameters4
text
string
required
The complete draft supplied as data for editing.
genre
string
optional
Publication context: social for LinkedIn or X; research and professional retain formal register.
audience
string
optional
Optional intended reader or destination when that context is not clear from the draft.
operation
string
optional
Optional local character cleanup only. Does not call an editing model or verify statistical watermark removal.
Raw schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 20000,
"description": "The complete draft supplied as data for editing."
},
"genre": {
"default": "general",
"description": "Publication context: social for LinkedIn or X; research and professional retain formal register.",
"type": "string",
"enum": [
"general",
"social",
"email",
"research",
"professional"
]
},
"audience": {
"description": "Optional intended reader or destination when that context is not clear from the draft.",
"type": "string",
"maxLength": 200
},
"operation": {
"description": "Optional local character cleanup only. Does not call an editing model or verify statistical watermark removal.",
"type": "string",
"const": "clean_text"
}
},
"required": [
"text"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
Remove AI writing patterns from your drafts without losing your core message. Zero Slop is a free, open-source anti-slop skill for Claude Code, Cursor and Codex.
It finds AI slop and workslop, guides the edit, and checks that the key details of your message survive. If your AI setup does not support agent skills, try the browser editor or use our MCP connector.
Why it exists
An AI draft can be grammatically sound and still read like workslop. In a compatible AI assistant, Zero Slop flags slop patterns, then guides the edit. The writing score finds patterns worth reviewing; it cannot tell who wrote the text.
See an edit
Let's see Zero Slop at work. Imagine using AI to write a linkedin launch announcement and getting this:
We're thrilled to announce that our team has leveraged cutting-edge machine learning to deliver a seamless onboarding experience, reducing setup time by 40%.
The local Python scorer in Zero Slop scores the input Slop score 99.3/100. A high Slop score means the draft is more likely to contain sloppy patterns.
Zero Slop then strips the patterns and guides the AI agent to produce the deslopped output below:
We used machine learning to reduce onboarding setup time by 40%.
text
Writing score: 9.5/100 [clear]
Flagged phrases : 0 across 10 words
Quick start
The installed skill can make an optional, metadata-only request to GitHub’s public releases API to check for updates. It sends no draft or private learning data. Set ZS_NO_UPDATE_CHECK=1 to disable it. Hosted MCP requests are separate and are covered by our privacy policy.
You can try the browser editor without installing anything, install the skill in an assistant that supports skills, or use the hosted service through MCP and the API.
If you use Claude Code, Codex, or another assistant that supports skills, here's how to install Zero Slop there:
sh
npx skills add manavmishra/ZeroSlop --global
text
/zero-slop (your writing)
To see the flagged passages without an edit, use /zero-slop inspect (your writing).
The command above works with Claude Code and Codex. In Claude.ai, upload the skill ZIP. Other installation paths include Gemini CLI and remote MCP connections where your client allows them. You can also score a file locally without a model call.
What it does
Your AI assistant, whether Claude, GPT, or another compatible model, reads and edits the draft. The skill supplies the workflow and local tools: a 0 to 100 writing score, source-detail checks, and a final comparison with the original.
What it catches
The scorer uses 294 weighted patterns and a 96-term lexicon. It checks for:
binary contrast formulas: “It's not X. It's Y.”
canned openers: “We're thrilled to…” and “Here's the thing…”
vague attribution: “experts agree” and “studies show”
significance inflation: “marks a pivotal moment” and “a testament to”
promotional wording: “robust,” “seamless,” and “leverage” when used as hype
repeated sentence shapes, crowded statistics, and overworked formatting
The editing workflow
The Zero Slop agent uses an eight-stage workflow. Each stage is a job with a role, not a separate model; some run in the Python tools and others run in the user's AI app. We treat eight stages as an engineering convention, not eight separate models.
Stage
Job
1. Scorer
Find exact phrases, pacing problems, readability issues, and overworked formatting.
2. Interpreter
Read the claims, audience, structure, and voice before editing.
Catch stumbles, repetition, and awkward transitions.
7. Verifier
Compare the edit with the source for meaning, qualifiers, voice, and format.
8. Fresh-eyes finalizer
Apply only safe final polish, then run one last local check.
Evidence and limits
A saved, same-model editing test
We ran Zero Slop and three other open-source agent skills on our AI Slop test corpus, using GPT-5.4, high reasoning, and pinned instructions. Saved outputs are reproducible.
Method
Mean writing score ↓
Passed local gates
Source check passed
Mean length change
Original drafts
76.3
0/18
—
—
Zero Slop
12.8
18/18
18/18
-8.9%
avoid-ai-writing
23.3
15/18
18/18
-14.6%
no-ai-slop
28.4
12/18
17/18
-13.7%
humanizer
35.4
9/18
17/18
-7.2%
Our RAID+ audit scored 7,627 non-empty machine-generated abstracts from four models. The INSCONE project extended RAID by generating new outputs from the original RAID prompts.
Model
Texts scored
Mean writing score ↓
At or above 25
DeepSeek V3
1,995
14.5
10.1%
Gemini 3.1 Pro
1,998
17.0
18.2%
Gemma 3 27B
1,634
21.6
30.4%
Llama 3.3 70B
2,000
25.5
41.7%
RAID+ records which model wrote each passage, not whether it reads well.
Documented features
This is a feature comparison of Zero Slop against other popular slop tools.
You can teach Zero Slop a preference by giving it the original output, your edited version, and the reason for the change. Private data stays under $ZERO_SLOP_HOME and follows your privacy settings. Zero Slop is an AI slop detector and editor, not a plagiarism tool.
For Gemini CLI, run gemini extensions install https://github.com/manavmishra/ZeroSlop --auto-update. For file-upload assistants, download the single-file bundle.
Local scoring
Score a file without sending it to a model:
sh
npx zero-slop score draft.md
From a cloned checkout, check a folder against the review threshold of 25:
The CLI sends a file to the hosted editor without changing the file on disk:
sh
npx --yes zero-slop@2.12.39 deslop draft.md --genre professional
Use - for stdin and --json for structured output. --require-approved prints the result but exits nonzero when review is needed. Requires Node.js 22+; offline score also needs Python 3. CLI options and privacy.
Direct installs, marketplace submissions, and release synchronization
Contribute or get help
Found a false positive, a broken check, or a better example? Use the issue forms or start a Discussion. If you want to change a pattern, read CONTRIBUTING.md and include tests with your pull request.