Short-form hook styles, script structures, retention and CTA rules for creators.
If you already use Content, the content mcp server is the piece that lets your assistant work with it directly. Short-form hook styles, script structures, retention and CTA rules for creators.
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.
Installation goes through your MCP client rather than a global install: point it at content-hooks-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
get_hook_mechanics — 10 hook styles as fill-in structures with why each works + failure modeaudit_hook — PASS/NEEDS WORK on a hook line: 2-second window, greetings, hype vs receipts, style detectionget_script_structure — Beat-by-beat timing for talking_head, voiceover_broll, tutorial, storytime, ugc_adaudit_script — Full script audit: hook, spoken length, single-CTA law, zero-numbers checkget_retention_mechanics — Open loops, payoff scheduling, pattern breaks, specificity ladders, loop endingsget_cta_rules — CTA rules by goal (follow, comment seed, lead magnet, product, save/share)get_full_pack — Everything in one payload for agent contextAmong the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Content's toolset — get_hook_mechanics, audit_hook, get_script_structure and 4 more — is a fair guide to whether it matches your workflow. It is maintained by closermethod; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| 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 |
Claude Desktop config:
```json
{ "mcpServers": { "content-hooks": { "command": "npx", "args": ["content-hooks-mcp"] } } }Configuration as documented by the project. Restart the client after saving.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.