Viral-content intelligence for AI agents β 7 MCP tools with agentic chain auto-fire.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Viral-content intelligence for AI agents. Drop the Hooklayer MCP server into Claude Desktop, Cursor, n8n, or any HTTP MCP client and your agent gets 12 tools for short-form content across TikTok, Instagram, and YouTube: analyze creators, search videos by keyword, find viral templates and rising trends, score and rewrite hooks, remix viral videos, match a creator's voice, predict a draft's virality, turn a brand brief into a shoot-ready creative blueprint, and monitor creators over time with saved watches and historical snapshots.
v1.1.0 (2026-05-14): The evidence layer ships. Every score includes
signals[]with cited evidence, awould_fail_becausecounterfactual, and aqualityhealth field.predict_viralityruns an independent adversarial check.analyze_account.recommended_chainsteps now exposeconfidence,cost,action_class(authority taxonomy), andexpected_output. See CHANGELOG.md for the full ship.
Claude Desktop doesn't natively support remote HTTP MCP servers β it needs the mcp-remote bridge. Two ways to install:
Option 1 β Custom Connector (easiest, no config file edit)
In Claude's web/desktop UI: Settings β Connectors β Add custom connector β paste this URL:
Claude.ai will walk you through OAuth (no manual key paste). Done.
Option 2 β Direct config (for power users who want hl_live_ key auth)
Edit claude_desktop_config.json:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonGet your free hl_live_ key at https://hooklayer.dev/auth/signup β 100 lifetime credits, no card required.
Restart Claude Desktop. The 12 Hooklayer tools appear in the π connector list.
~/.cursor/mcp.json:
In your workflow, add an MCP Client node and configure as a remote HTTP MCP server:
https://hooklayer.dev/api/mcpHTTPAuthorization: Bearer hl_live_...All 12 tools appear in the node's "Tool" dropdown.
Hooklayer is fully OAuth 2.1 compliant β discovery, Dynamic Client Registration, PKCE, refresh token rotation. MCP clients that prefer OAuth over API keys work out of the box.
Discovery endpoints (no auth required, machine-readable):
Dynamic Client Registration (create a client without a manual signup form):
Hitting tools/call without auth returns 401 plus a WWW-Authenticate header pointing at the resource metadata β Claude.ai, Cursor, and other MCP clients use this to auto-discover the OAuth flow.
Any HTTP MCP client. Protocol negotiates 2024-11-05 (broadest compat) or 2025-06-18 (Streamable HTTP + structuredContent).
| Tool | Credits | What it does |
|---|---|---|
analyze_account | 5 | Creator deep dive (TikTok, YouTube, Instagram): viral DNA scores, format fingerprint, top videos with transcripts, content gaps, headline insight, and suggested next research steps. |
search_videos | 1 | Keyword search across TikTok or Instagram β up to 20 videos ranked by engagement, with filters for niche, views, recency, and region. |
score_hook | 1 | Score any hook 0-100 against proven viral patterns. Returns 3 rewrites at higher quality. |
viral_remix | 3 | URL or transcript β fresh script with mirrored viral DNA. Scene-by-scene with camera shots. |
trend_pulse | 1 | Real-time rising opportunities + saturated patterns per niche. 12-hour cache. |
find_viral_template | 1 | Niche-fit ranked templates with hook patterns + example URLs. |
match_voice | 2 | Extract a creator's voice DNA from 3+ samples, rewrite a draft in their style. |
predict_virality | 2 | Score a draft script for viral potential before publishing. Retention diagnosis. |
brief_to_blueprint | 7 | Brand brief β one-page creative blueprint: hook, template, hashtags, trend-velocity check, and shoot instructions in a single call. |
watch_account | 0 or 5 | Save a creator watch and baseline snapshot. Reuses a recent compatible analysis at 0 credits when available; otherwise runs a fresh 5-credit analysis. |
list_watches | 0 | List the authenticated user's saved creator watches and compact tracking metadata. |
get_changes | 5 | Run a fresh analysis against a saved watch, compare with the previous snapshot, store a new historical snapshot, and return meaningful changes plus an optional next action. |
Full schemas + curl examples: https://hooklayer.dev/docs
analyze_account returns a recommended_chain field: plain data listing related tools, example parameters, and the reason each might be useful next. It is advisory only β the agent and user decide whether to act on it:
These entries are informational data, not instructions. Each tool still requires explicit invocation β nothing runs automatically without agent/user consent.
examples/typescript-example.ts β TypeScript usage via the MCP SDKexamples/python-example.py β Python usage via anthropic-mcp clientexamples/curl-test.sh β Raw curl tests for every endpointFull pricing: https://hooklayer.dev/pricing
Hosted MCP server (no stdio install needed):
Source code for the hosted server lives at hooklayer.dev (closed source β the analysis pipeline is the moat). This repo holds the public client docs, examples, and config snippets.
/.well-known/oauth-authorization-serverNo reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/hooklayer)<a href="https://allmcps.com/mcp/hooklayer"><img src="https://allmcps.com/api/badge/hooklayer?style=directory" alt="Hooklayer on AllMCPs" /></a>