Zero Slop
Summary: The server provides one deslop tool for cleaning AI-slop patterns from prose while scoring it and checking source preservation.
Edit pasted text (1–20,000 chars) with optional
genreandaudiencecontext; returns rewritten or unchanged text.Get before/after scores, flagged phrases, readability, sentence variety, register/shape/punctuation metrics, and score change.
Verify facts/source details and final checks, returning warnings, status, model-request counts, and editor diagnostics.
Use
operation: "clean_text"for local character cleanup only, without a model call or watermark-removal verification.Hosted editing uses Cloudflare Workers AI first and may fall back to OpenRouter free providers that may retain or train on drafts.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Zero Slop
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.
Related MCP server: WSC - Writing Style Checker
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 wordsQuick 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% |

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.

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/mcpFor 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.mdFrom a cloned checkout, check a folder against the review threshold of 25:
python3 scripts/slopscore.py --batch drafts/ --gate 25Command line
The CLI sends a file to the hosted editor without changing the file on disk:
npx --yes zero-slop@2.12.40 deslop draft.md --genre professionalUse - 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:
curl --fail-with-body --max-time 75 https://mcp.zero-slop.ai/v1/deslop \
-H 'Content-Type: application/json' \
--data '{"text":"Maya owns the pricing review.","genre":"professional"}'Check status before using an edit. Shared free capacity accepts up to 20,000 Unicode code points after trimming. API reference · OpenAPI contract
Find the source
Path | Purpose |
The complete detect, rewrite, verify, and learn workflow | |
Offline meter and source-detail gate | |
Performed-register and reading pass | |
Genre guidance, tells, safeguards, and evaluation rules | |
Reproducible before-and-after edits | |
Frozen benchmarks, provenance, and limitations | |
Optional hosted MCP server documentation | |
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.
For setup help, see SUPPORT.md. Report security issues through SECURITY.md.
Credits
Zero Slop builds on ideas from First Reader, no-ai-slop, humanizer, de-slop, stop-slop, unslop-text, and avoid-ai-writing.
License
Available Tools
1 tooldeslopDeslop writingAInspect
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.
Inputs: text (required), genre, audience, operation. Returns: note, text, after, before, +11 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong one. Its purpose (edit pasted prose with scoring and source-preservation checks) is clearly stated in the description.
The lone name 'deslop' is lowercase, concise, and action-oriented, so there is no internal inconsistency. With a single tool, no repeatable verb_noun pattern can be established, which keeps it just short of a 5.
A single tool for a single-purpose editing service is defensible, but the surface is thin: scoring, checks, and editing are all bundled into one opaque call with no granular operations. Users cannot request scoring-only or a review-only pass without triggering an edit.
The one tool covers the core edit-and-score workflow and returns scores, checks, and warnings, but there are notable gaps: no standalone scoring/checking operation, no batch or multi-draft support, and no way to configure or constrain the editing behavior. Agents must work around these by parsing bundled outputs.
Maintenance
Related MCP Connectors
Use AI. Skip the slop. A Slop score plus the exact lines that sound like chatbot writing.
An editor to finish what you write with your AI: checks, reviews, and your own edits on one draft.
Paste a draft and see the habits that make writing read like it came from an AI model.
Scan manuscript text for AI-slop prose patterns before publishing to Amazon KDP.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables detection and elimination of AI slop in text, providing tools to analyze writing for overused phrases, structural issues, and verbosity, and offers human writing rules tailored to context.33MIT
- AlicenseAqualityBmaintenanceFlag AI tells, weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, and filler adverbs49MIT
- AlicenseAqualityCmaintenanceThree deterministic MCP tools that score text for AI-writing tells (em-dash density, hedge words, tricolons, boilerplate openers) and grade landing-page copy. No LLM, no network calls, no API key — same input always yields the same score. Published on the official MCP registry as io.github.parweb/ai-slop-checker.3MIT
- FlicenseNot gradedqualityAmaintenanceEnables agents to analyze prose for formulaic AI writing patterns and return a 0–100 score, band label, violations with context, and concrete advice through its MCP tools.-