Zero Slop
Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
Install Zero Slop
Pick your client, then add it in one click or paste the config.
~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"zero-slop": {
"command": "npx",
"args": [
"-y",
"zero-slop"
]
}
}
}
Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.
Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.
Overview
Security & health
What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.
Recent health check succeeded.
Supply-chain signal
No high-severity advisories surfaced by our automated scan.
Scanned 12d ago via OSV.dev · zero-slop (npm)
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
From the project README
Zero Slop
Find and remove AI slop in your writing. Get rid of workslop without losing your core intent and message.
Zero Slop is a free, open-source agent skill that finds and removes AI slop while checking that the core details of your message survive the edit. 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%.
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:
npx skills add manavmishra/ZeroSlop --global
/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. |
| 3. Rewriter | Remove stock language without inventing detail. |
| 4. Fact gate | Check names, numbers, quotations, links, code, tables, paths, and structure locally. |
| 5. Copy desk | Fix grammar, usage, spelling, and consistency. |
| 6. Read-aloud editor | 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% |
The RAID+ audit asks a different question: how much default writing from different models is flagged as AI slop by Zero Slop? The test corpus contains 7,627 anonymous, user-generated transcripts:
| 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.
The checks draw on research into predictable machine wording and overused vocabulary. Zero Slop cannot identify an author: detectors can misclassify non-native English.
Private learning
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 developers: other ways to access Zero Slop
Hosted MCP
The endpoint for compatible clients is:
https://mcp.zero-slop.ai/mcp
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:
npx zero-slop score draft.md
From a cloned checkout, check a folder against the review threshold of 25:
python3 scripts/slopscore.py --batch drafts/ --gate 25
Command line
The CLI sends a file to the hosted editor without changing the file on disk:
npx --yes zero-slop@2.12.26 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.
REST API
The REST API accepts the same edit request:
Reviews
No reviews yet — be the first to share how it worked for you.
Frequently Asked Questions about Zero Slop
Related MCP servers
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/zero-slop)<a href="https://allmcps.com/mcp/zero-slop"><img src="https://allmcps.com/api/badge/zero-slop?style=directory" alt="Zero Slop on AllMCPs" /></a>