Slop or Not

resmi

Apple silicon üzerinde yerel olarak çalışan, yapay zeka tarafından oluşturulmuş metin ve görselleri tespit etme, okunabilirliği puanlama ve yapay zeka izlerini temizleme araçları.

Slop Or Not MCP ile neler yapabilirsiniz?

  • Check app and Pro status — Confirm the local app is installed, the binary runs, and Pro is active before starting a detection workflow.
  • Detect AI text — Score a passage with the on-device model and get a verdict, score, language, sentence count, and readability metrics.
  • Analyze readability — Compute reading-level metrics for a passage without running AI detection.
  • Clean text artifacts — Strip zero-width characters, homoglyphs, and fancy punctuation before a detection pass.
  • Detect AI images — Check JPEG, PNG, HEIC, or WebP image bytes locally with provenance reads and an on-device model fallback.
  • Find writing tells — Flag stock phrases and AI vocabulary in English text, with positions and lesson links where available.

Dokümantasyon

On-device AI detector scoring

AI Content Detector MCP for Claude, Codex, and Cursor

The Slop or Not MCP server lets Claude, Codex, Hermes Agent, OpenClaw, Cursor, and other agents call a local AI text detector, AI image detector, readability analyzer, and cleanup tool on your Mac.

Point your MCP client at the bundled slop mcp command and try one free check a day. With Pro, Claude, Codex, Hermes Agent, OpenClaw, Cursor, and other agents keep running local checks without a daily cap or per-call metering.

On-device

Client setup snippets point at the bundled Mac app binary.

Local stdio server

Your MCP client starts the bundled slop binary and talks to it over stdio.

Text and Image Tools

Status, text detection, readability, cleanup, image detection, and raw image scoring.

Free to Try

Try one free check a day; Pro removes the cap and adds cleanup, readability and raw image scoring.

Set Up With Your AI Agent

Paste this prompt into Claude Code, Codex, or Cursor, and your agent finds Slop or Not, checks that it runs, and sets it up for you. It asks before it edits your shell profile or another app's settings.

Copy prompt

Download https://slopornot.ai/agent-setup.md with curl, read it in full, and follow it to set up Slop or Not for me.

Client setup

How do I add Slop or Not to an MCP client?

Install the Mac app, open it once, then use the app-bundle snippet for your client. Claude, Codex, Hermes Agent, OpenClaw, and Cursor all point at the same local server. Set it up once and every agent session after that reuses it, with no reinstall and no new login. Without Pro you get one free check a day, and Pro or the free trial lifts the cap.

Claude Code

Add Slop or Not as a user-scoped stdio server, restart Claude Code, then verify with /mcp.

Copy

claude mcp add --transport stdio --scope user SlopOrNot -- "/Applications/Slop Or Not.app/Contents/MacOS/slop" mcp

Claude Desktop

Use this JSON shape in ~/Library/Application Support/Claude/claude_desktop_config.json, then quit Claude Desktop fully and relaunch it.

Copy

{
  "mcpServers": {
    "SlopOrNot": {
      "command": "/Applications/Slop Or Not.app/Contents/MacOS/slop",
      "args": ["mcp"]
    }
  }
}

Codex

Run codex mcp add in Terminal, or add the server to ~/.codex/config.toml yourself. Restart Codex so it reads the new MCP server list.

Copy

codex mcp add SlopOrNot -- '/Applications/Slop Or Not.app/Contents/MacOS/slop' mcp

Prefer to edit the file? Add this to ~/.codex/config.toml instead:

Copy

[mcp_servers.SlopOrNot]
command = "/Applications/Slop Or Not.app/Contents/MacOS/slop"
args = ["mcp"]

Hermes Agent

Add Slop or Not as an MCP server in your Hermes Agent config, then restart Hermes Agent so it can call the local tools.

Copy

mcp_servers:
  SlopOrNot:
    command: "/Applications/Slop Or Not.app/Contents/MacOS/slop"
    args: ["mcp"]

OpenClaw

Register Slop or Not with the OpenClaw MCP CLI, then run mcp doctor with --probe to confirm the server answers.

Copy

openclaw mcp set SlopOrNot '{"command":"/Applications/Slop Or Not.app/Contents/MacOS/slop","args":["mcp"]}'
openclaw mcp doctor SlopOrNot --probe

Cursor

Add this to ~/.cursor/mcp.json for a global server, or .cursor/mcp.json at the project root for one project.

Copy

{
  "mcpServers": {
    "SlopOrNot": {
      "command": "/Applications/Slop Or Not.app/Contents/MacOS/slop",
      "args": ["mcp"]
    }
  }
}

Tool reference

What tools does the Slop or Not MCP server provide?

The server provides the checks agents usually need: status, text detection, readability, cleanup, image detection, and raw image scoring, plus writing tells from 1.3.

Every result below was captured from Slop or Not for Mac and abridged where marked. Most come from version 1.1.1 (August 2026), and the entry marked New in 1.3 from 1.3.0 (November 2026).

slop_status

Check app and Pro status

Confirms the app is installed, the binary can run, and Pro is active before the agent starts a workflow.

View payload and result

Tool input

Copy

{}

Result shape

Copy

{
  "pro": true,
  "version": "1.1.1"
}

detect_text

Detect AI text

Scores a passage with the on-device AI text detection model and returns a verdict, score, language, sentence count, and readability metrics.

View payload and result

Tool input

Copy

{
  "text": "<text>",
  "include_readability": true,
  "language_code": "en",
  "locale": "en-US"
}

Result shape

Copy

{
  "kind": "result",
  "verdict": "most_likely_real",
  "score": 0.1259,
  "language": "en",
  "sentence_count": 2,
  "generator": null,
  "input_truncated": false,
  "readability": {
    "language": "en",
    "language_confidence": 0.9998,
    "scores": [
      { "kind": "fleschReadingEase", "value": 50.85, "label": "Fairly difficult", … },
      { "kind": "fleschKincaidGradeLevel", "value": 16.97, … }
    ],
    "word_count": 87,
    "sentence_count": 2,
    "avg_words_per_sentence": 43.5,
    "warnings": [ … ],
    "full": { "consensus": { … }, "genre": { … }, "grade_label": { … }, … }
  }
}

analyze_readability

Analyze readability

Computes reading-level metrics without running AI detection.

View payload and result

Tool input

Copy

{
  "text": "<text>",
  "language_code": "en",
  "locale": "en-US"
}

Result shape

Copy

{
  "language": "en",
  "language_confidence": 0.9998,
  "scores": [
    { "kind": "fleschReadingEase", "value": 50.85, "label": "Fairly difficult", … },
    { "kind": "fleschKincaidGradeLevel", "value": 16.97, … }
  ],
  "avg_words_per_sentence": 43.5,
  "sentence_count": 2,
  "word_count": 87,
  "warnings": [ … ],
  "full": { "consensus": { … }, "genre": { … }, "grade_label": { … }, … }
}

clean_text

Clean text artifacts

Strips zero-width characters, homoglyphs, and fancy punctuation before the next detection pass.

View payload and result

Tool input

Copy

{
  "text": "<text>",
  "language_code": "en",
  "remove_invisibles": true,
  "remove_punctuation": true,
  "remove_homoglyphs": true,
  "britishize": false
}

Result shape

Copy

{
  "cleaned_text": "He said \"hello\" - and left.",
  "language": "en",
  "removed_invisibles": 1,
  "punctuation_replacements": 3,
  "homoglyphs_replaced": 0,
  "british_substitutions": 0
}

detect_image

Detect AI images

Checks JPEG, PNG, HEIC, or WebP image bytes locally with C2PA and IPTC provenance reads and an on-device model fallback. The result names its detection_source, so an agent can tell a provenance hit from a model score.

View payload and result

Tool input

Copy

{
  "image_base64": "<base64>",
  "recognize_text": false
}

Result shape

Copy

{
  "kind": "result",
  "verdict": "probably_ai_slop",
  "score": 0.6429,
  "generator": null,
  "detection_source": "ml",
  "watermark_provider": null,
  "watermark_confidence": null,
  "recognized_text": null,
  "recognized_sentence_count": null
}

score_image

Score AI images

Returns the raw image-model score without the full provenance-aware image-detection response. Requires the AI image detection model to be installed.

View payload and result

Tool input

Copy

{
  "image_base64": "<base64>"
}

Result shape

Copy

{
  "raw_slop_score": 0.33984375
}

analyze_writing_tellsNew in 1.3

Find Writing Tells

Finds stock phrases, AI vocabulary, and other writing patterns common in AI-generated text. Each match comes back with its position and, where one exists, a link to the lesson. It reads English only and never changes the AI score. Requires Pro or the free trial.

View payload and result

Tool input

Copy

{
  "text": "<text>"
}

Result shape

Copy

{
  "analysis": {
    "flaggedSentences": [
      { "end": 111, "matchIndexes": [0, 1], "start": 0 }
    ],
    "matches": [
      { "end": 27, "id": "landscape", "start": 0, "text": "In today's fast-paced world" },
      { "end": 56, "id": "note-that", "start": 29, "text": "it's important to note that" }
    ],
    "perPattern": { …, "landscape": 1, …, "note-that": 1, … },
    "regions": [ … ],
    "wordCount": 15
  },
  "contract_version": 62,
  "language": "en",
  "lexicon_version": "2026-09-15",
  "patterns": [
    {
      "category": "phrase",
      "count": 1,
      "id": "note-that",
      "lesson_url": "https://slopornot.ai/tells/its-important-to-note?utm_source=macos_app",
      "name": "\"It's important to note\"",
      "severity": "strong"
    },
    {
      "category": "vocabulary",
      "count": 1,
      "id": "landscape",
      "name": "\"Ever-evolving landscape\"",
      "severity": "moderate"
    }
  ],
  "status": "analyzed"
}

Verify

How do I verify the MCP server?

After restart, ask your agent to run slop_status. The expected result is a tool call that reports the local app and Pro state without an error. A call that needs Pro comes back as a tool error (isError: true) while the server keeps running, so one blocked call never ends the session.

Copy

{
  "pro": true,
  "version": "1.1.1"
}

Security

Trust the source

Only register MCP servers you trust. The Slop or Not MCP server is bundled with the signed Mac app, and the snippets on this page point at that exact app-bundle binary.

Troubleshooting

Why do the snippets use the app-bundle path?

GUI agents can launch outside your login shell, where command names may not resolve. The snippets use the signed app-bundle path so each client starts the same bundled Slop or Not binary.

Installed Slop or Not a while back? Older installs are named Slop Or Not - AI Fake Detector.app, so change the path in your snippet to match, or paste the setup prompt and let your agent find the app. On OpenClaw, remove an old lowercase slopornot entry before you add SlopOrNot.

Local API

Can agents use this instead of a cloud AI detector API?

For agent workflows, yes. MCP gives Claude, Codex, Hermes Agent, OpenClaw, Cursor, and other clients a local tool interface instead of a hosted AI detector API. The client sends text or image data to the bundled Mac binary over stdio, and the check runs on your Mac.

Loop with agents

How does Slop or Not work with the agentic AI Humanizer skill?

The agentic AI Humanizer skill can run core rewriting and voice matching without Slop or Not. Connect it to Slop or Not with Pro active when you want MCP tools to score a baseline, run Text Cleanup before and after humanization, re-score with the on-device AI detector, and show cleanup stats. Your writing sample steers the rewrite; Slop or Not supplies local AI detector measurement.

Slop or Not returns a probability verdict, not proof of authorship. Results can vary with new AI models, short passages, and writing that was heavily edited by a human.

Claude Code MCP guideAgentic AI Humanizer setup guideRead the MCP and CLI launch postRead the voice-matching guideUse the CLI instead