Skip to main content
Glama
creator-ops-mcp

creator-ops-mcp

creator-ops-mcp

npm version License: MIT MCP Compatible

Deterministic creator-ops layer for AI coding agents: turn any transcript into ranked Shorts, safe chapters, high-CTR metadata, and thumbnail briefs—locally, explainably, and without API keys.

Features

  • 🎯 Ranked Viral Shorts — Mathematical ShortScore ranking of your best clip candidates

  • 📑 Non-Spoiling Chapters — YouTube chapters with curiosity-preserving category labels

  • 🔤 5-Archetype Title Matrix — Psychologically-tuned titles across proven CTR frameworks

  • 🖼️ Thumbnail Briefs — Visual prompt specs for Midjourney/Flux, rule-of-thirds composed

  • 🔒 Zero API Keys — Works fully offline with local .srt/.vtt/.txt files

  • ✅ Compliance Auditing — Flags clickbait, demonetization triggers, and PII

Related MCP server: YouTube Transcript + Search MCP

ShortScore Formula

ShortScore = 0.30·H + 0.20·R + 0.20·E + 0.15·P + 0.10·C + 0.05·S

Weight

Component

Description

0.30

H — Hook Strength

First-3-second pattern score (bold claim, curiosity gap, direct stakes, contradiction, numbered specificity, before/after, immediate conflict)

0.20

R — Retention Arc

Open-loop setup + payoff resolution within the clip

0.20

E — Emotional Trigger

Weighted emotion classes: fear/loss (16), greed/gain (15), shock (14), curiosity (14), status (13), validation (12)

0.15

P — Pacing

Concept density, dead-zone penalty (>18 sec without new beat)

0.10

C — Clarity

Filler rejection, pronoun ambiguity checks

0.05

S — Safe-to-Clip

Compliance clearance, no dangling references

Hard Rejection Rules

Clips are automatically rejected if they:

  • Start with filler phrases: "hey guys", "welcome back", "in this video", etc.

  • Contain unresolved pronouns in the first sentence ("it", "this", "they" without context)

  • Have dead zones longer than 18 seconds without a new concept or narrative beat

Setup

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "creator-ops": {
      "command": "npx",
      "args": ["-y", "creator-ops-mcp"]
    }
  }
}

Claude Code

claude mcp add creator-ops -- npx -y creator-ops-mcp

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "creator-ops": {
      "command": "npx",
      "args": ["-y", "creator-ops-mcp"]
    }
  }
}

Available Tools

extract_shorts_hooks

Analyzes a transcript and returns ranked Shorts candidates with ShortScores.

Input:

{
  "transcript": { "filePath": "/path/to/video.srt" },
  "context": {
    "contentType": "tutorial",
    "tone": "educational",
    "targetDurationSec": 60
  }
}

generate_chapters

Generates non-spoiling YouTube chapters from a transcript.

Input:

{
  "transcript": { "rawTranscript": "00:00 Introduction\n..." },
  "context": { "spoilerPolicy": "strict" }
}

generate_seo_metadata

Produces a 5-archetype title matrix + thumbnail brief.

Input:

{
  "transcript": { "filePath": "episode.vtt" },
  "context": { "contentType": "podcast", "tone": "conversational" }
}

audit_compliance

Scans transcript and metadata for risk flags before publishing.

Input:

{
  "transcript": { "rawTranscript": "..." },
  "metadata": { "title": "...", "description": "..." }
}

Supported Transcript Formats

Format

Extension

Notes

SubRip

.srt

Standard subtitle format with millisecond precision

WebVTT

.vtt

Web video text tracks, strips styling tags

Plain Text

.txt

Synthetic timecodes at ~150 wpm

YouTube URL

https://youtube.com/...

Keyless public caption extraction

Development

git clone https://github.com/kartiksingh02777/creator-ops-mcp
cd creator-ops-mcp
npm install
npm run build
npm test

License

MIT © Kartik Singh (kartiksingh02777)

Available Tools

4 tools
audit_complianceA

Scan a transcript and optional metadata for compliance risks before publishing. Detects clickbait overpromise, profanity/demonetization triggers, sensitive claims (medical/financial/legal), PII leaks (phone, email, SSN), and copyright signals. Returns overall risk level, per-flag severities, monetization safety, and publish-readiness.

Inputs: transcript (required), metadata.

extract_shorts_hooksA

Analyze a transcript and return ranked YouTube Shorts candidates scored by the ShortScore formula (0.30·H + 0.20·R + 0.20·E + 0.15·P + 0.10·C + 0.05·S). Applies hard rejection rules for filler starts, dangling pronouns, and dead zones.

Inputs: transcript (required), context, maxResults.

generate_chaptersB

Generate non-spoiling YouTube chapters from a transcript. Chapters use the [Searchable Subject] + [Non-Spoiling Outcome Category] formula. The first chapter always starts at 00:00. Spoiler guard replaces reveal-type titles with curiosity categories based on spoilerPolicy.

Inputs: transcript (required), context, minChapterDurationSec.

generate_seo_metadataB

Generate a 5-archetype title matrix (Curiosity Gap, FOMO, Before/After, Extreme Contrast, Authority/Proof) plus a visual thumbnail brief in Midjourney and Flux prompt formats. All titles are under 60 characters. Returns suggested description and tags.

Inputs: transcript (required), context, existingTitle.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each of the four tools targets a clearly distinct output: ranked shorts candidates, chapter markers, SEO title/thumbnail matrix, and a compliance risk report. There is no plausible scenario where these overlap, and the descriptions reinforce the boundaries.

    Naming Consistency5/5

    All names follow a consistent snake_case verb_noun pattern (extract_*, generate_*, generate_*, audit_*), with verbs that accurately reflect each action. The naming is predictable and readable.

    Tool Count4/5

    Four tools is well-scoped for a transcript-processing creator-ops pipeline and each earns its place. It sits at the thin end, but nothing feels redundant or missing for the stated purpose.

    Completeness4/5

    The surface covers the core post-transcript workflow: shorts extraction, chapters, SEO metadata (titles, description, tags), and pre-publish compliance. Minor gaps exist, such as no transcript ingestion/preprocessing or analytics/publishing step, but the set is usable end to end.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI clients to pull full transcripts from YouTube videos, search videos and channels, browse a channel's complete upload history, search within a single channel, and extract every video in a playlist through one hosted remote endpoint. It supports API-key or OAuth 2.1 sign-in with no local installation, returning metadata and paginated results with stable error codes.
      10
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to retrieve YouTube transcripts, video info, channel video lists, and monitor channels for new uploads, with built-in prompt templates for summaries and industry signals—all without an API key.
      4
      MIT
    • F
      license
      B
      quality
      B
      maintenance
      Enables creators to analyze supplied short-form video transcripts and metadata into structured hook, retention, remix, script, content-gap, and creator-pack outputs without API keys or paid external services.
      8
      -