Content Hooks MCP
# Content Hooks MCP
**Short-form content mechanics for AI agents: hooks, script structures, retention, CTAs. The first 2 seconds decide the next 28.**
> **Disclaimer.** Structured content-mechanics frameworks from documented short-form practice. Platforms change; specificity and payoff don't.
## Why This Exists
AI agents drafting short-form content default to the same failure: greeting openers, hype adjectives, three ideas per video, and four CTAs. This MCP gives the agent the mechanics that survive contact with the feed — and auditors that fail drafts before they cost a post.
The house rule everything here enforces: **receipts over hype.** A number you can screenshot beats any adjective.
## 7 Tools
| Tool | What it returns |
|---|---|
| `get_hook_mechanics` | 10 hook styles as fill-in structures with why each works + failure mode |
| `audit_hook` | PASS/NEEDS WORK on a hook line: 2-second window, greetings, hype vs receipts, style detection |
| `get_script_structure` | Beat-by-beat timing for talking_head, voiceover_broll, tutorial, storytime, ugc_ad |
| `audit_script` | Full script audit: hook, spoken length, single-CTA law, zero-numbers check |
| `get_retention_mechanics` | Open loops, payoff scheduling, pattern breaks, specificity ladders, loop endings |
| `get_cta_rules` | CTA rules by goal (follow, comment seed, lead magnet, product, save/share) |
| `get_full_pack` | Everything in one payload for agent context |
## Install
```bash
npx content-hooks-mcp # once published to npm
# or from source:
git clone https://github.com/closermethod/content-hooks-mcp && cd content-hooks-mcp && npm i && npm run build && node dist/main.js
```
Claude Desktop config:
```json
{ "mcpServers": { "content-hooks": { "command": "npx", "args": ["content-hooks-mcp"] } } }
```
## The Family
Get seen (this one) → get positioned ([personal-brand-mcp](https://github.com/closermethod/personal-brand-mcp)) → get the reply ([outbound-engine-mcp](https://github.com/closermethod/outbound-engine-mcp)) → price the deal ([creator-deals-mcp](https://github.com/closermethod/creator-deals-mcp)) → own the audience ([newsletter-growth-mcp](https://github.com/closermethod/newsletter-growth-mcp)). Full catalog: [MCP Hub](https://elisabethhitz-mcp.netlify.app)
## Built By
[Elisabeth Hitz](https://www.linkedin.com/in/elisabethhitz) — 10+ years enterprise sales (Deel, Criteo, HBO), reverse-engineered for creators.
License: MIT
TDQS
Scored across 7 tools
Each tool targets a distinct aspect of content creation: hooks, script structure, retention, CTA rules, and audits. The full_pack tool provides a combined reference but does not overlap functionally, as it aggregates all reference materials for convenience.
Tool names follow a clear verb_noun pattern: get_ for retrieving reference materials and audit_ for analyzing content. The pattern is consistent and predictable, making it easy to infer tool purpose from the name.
Seven tools cover the core content-mechanics domain without bloat. Each tool serves a distinct educational or analytical function, and the count is well within the ideal range for a focused server.
The tool surface covers all major pillars of short-form content mechanics: hooks, script structures, retention, CTA rules, and audits. The full_pack provides a comprehensive reference, leaving no obvious gaps for the stated purpose.