Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@copy-unslop-mcp audit this landing page copy for AI clichés and readability"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Stop AI-sounding copy: skill + MCP verifier for landing pages, product UI, docs, emails and store listings, in English and Bahasa Indonesia, with readability scoring and SEO/microcopy length budgets.
An agent skill plus an MCP server in one package. The skill tells your coding agent what slop to avoid; the MCP tools then deterministically verify the result, so the agent can't just claim it's done.
Works with Claude Code, Claude Desktop, Codex and Antigravity.
Rule | Severity | Catches |
| ERROR | Stock AI-writing phrase. Say the specific thing: what it does, for whom, with what result. |
| WARN | Empty marketing adjective. Replace it with a concrete fact or number. |
| WARN | "It's not X, it's Y" contrast framing is a signature AI cadence. State Y directly. |
| WARN | Too many em dashes. |
| WARN | Too many exclamation marks. |
| ERROR | Link text that means nothing out of context (screen readers list links by text). Name the destination: "Read the pricing FAQ". |
| WARN | Generic button label. Say what happens: "Start free trial", "Download the report", "Book a 15-min demo". |
| WARN | Social proof or performance claim that is easy to fabricate. Use a real, sourced figure, or cut it. |
| WARN | Wordy filler phrase. Cut it or use the short form ("to", "because", "now"). |
| ERROR | Placeholder copy left in. Write the real text (or ask the user for it). |
| WARN | Emoji-led bullets and headings read as generated. Use plain bullets; keep emoji for tone, not structure. |
| ERROR | Frasa AI klise (bahasa Indonesia). Tulis hal spesifik: apa fungsinya, untuk siapa, hasilnya apa. |
Copy is extracted from markdown, HTML, JSX/TSX text and copy-like props (title, description, label, alt, ...) and i18n JSON. Readability uses Flesch/Flesch-Kincaid for English and switches to sentence-level metrics when it detects Indonesian.
Rules marked ERROR make the audit return status: "FAIL"; WARN is reported but does not fail.
Related MCP server: slop-guard
# Claude Code
claude mcp add copy-unslop -s user -- npx -y copy-unslop-mcp
# Codex
codex mcp add copy-unslop -- npx -y copy-unslop-mcpClaude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json) and Antigravity (~/.gemini/config/mcp_config.json):
{
"mcpServers": {
"copy-unslop": {
"command": "npx",
"args": ["-y", "copy-unslop-mcp"]
}
}
}Restart the app afterwards.
npx -y copy-unslop-mcp install-skills # clients that are installed
npx -y copy-unslop-mcp install-skills --all # every locationClient | Location |
Claude Code |
|
Codex |
|
Antigravity |
|
Claude Desktop has no skills folder, so it receives the rules through the MCP prompt and the load_*_rules tool.
Kind | Name | Purpose |
Prompt |
| The full skill text, for GUI clients |
Tool |
| Returns the full copy-unslop ruleset. Call before writing code if the copy-unslop skill is not already loaded. |
Tool |
| Deterministically scans markdown, markup, components and i18n JSON for copy slop: stock AI phrases (delve, unlock the power, seamless, in today's fast-paced world), empty marketing adjectives, 'not X but Y' framing, em-dash and exclamation overuse, 'click here' links, generic CTAs, unverifiable social proof, wordy filler, placeholder copy, emoji bullets, and Indonesian AI clichés. Accepts files or directories; with no files it audits the git working-tree changes. Suppress a verified false positive with a |
Tool |
| Scores prose (raw text, or copy extracted from md/mdx/html/jsx/tsx/i18n JSON): Flesch reading ease, Flesch-Kincaid grade, sentence length, longest sentences, repeated openers, passive voice, adverb density, em dashes. Detects Indonesian and skips English-only formulas. Run on any user-facing copy you wrote. |
Tool |
| Checks copy against channel length budgets: title, meta_description, og_title, og_description, headline, button, push_notification, sms, tweet, email_subject, app_store_subtitle, play_short_description. Pass items, and/or files to auto-extract , meta description, OG tags, Next.js metadata and markdown frontmatter. |
File paths resolve against the server's working directory and cannot escape it. Directories honour .gitignore and skip node_modules, build output and minified files.
The same audit runs without an agent. It exits 1 on any ERROR, so it works as a pre-commit hook or CI step:
npx -y copy-unslop-mcp audit # git working-tree changes
npx -y copy-unslop-mcp audit src app # files or directories
npx -y copy-unslop-mcp audit src --json # machine-readable
npx -y copy-unslop-mcp rules # list every ruleThe checks are regex and structure based: fast, offline and predictable, but heuristic. For a verified false positive, add a comment on the line or the line above, with a reason:
// unslop-ignore AI_TELL_PHRASE -- why this is safe hereSuppressions without a reason are reported as SUPPRESSION_WITHOUT_REASON errors, and every honoured suppression is listed in the audit output so reviewers can see it.
The agent loads the skill and writes code under its constraints.
Before finishing, the skill requires the audit and verification tools.
On FAIL, the agent fixes every finding and re-runs until PASS. Missing toolchains are reported as SKIPPED, never as passing.
All share the engine in unslop-core.
git clone https://github.com/fikrifirmanf/copy-unslop-mcp
cd copy-unslop-mcp && npm install
npm test # every rule is checked against its good/bad examples
node src/server.mjs # speaks MCP over stdioMIT © Fikri Firman Fadilah
This server cannot be deployed
Read-only canon of design and copy rules for AI agents to audit generated UI, served as resources.
Checks AI-written code against your rules as it is written, and keeps a record of what it found.
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
