Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Viral-content intelligence for AI agents — 7 read-only MCP tools, evidence-layer scoring.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http hooklayer https://hooklayer.dev/api/mcp --header 'Authorization: your-value'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"hooklayer": {
"url": "https://hooklayer.dev/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"hooklayer": {
"type": "http",
"url": "https://hooklayer.dev/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 khan-ashifur 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.1.0)于6个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Zoo MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
An MCP server that provides access to the Zoo API for various CAD operations and tools.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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.
12 tools · structured JSON · non-destructive creator monitoring · no external social-platform edits or deletes
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 — it needs the mcp-remote bridge. Two ways to install:
Option 1 — Custom Connector (easiest, no config file edit)
In Claude's web/desktop UI: Settings → Connectors → Add custom connector → paste this URL:
https://hooklayer.dev/api/mcp
Claude.ai will walk you through OAuth (no manual key paste). Done.
Option 2 — 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.json{
"mcpServers": { "hooklayer": { "command": "npx", "args": [ "-y", "mcp-remote@0.1.38", "https://hooklayer.dev/api/mcp", "--header", "Authorization:Bearer hl_live_..." ] } } }
Get your free hl_live_ key at https://hooklayer.dev/auth/signup — 100 lifetime credits, no card required.
Restart Claude Desktop. The 12 Hooklayer tools appear in the 🔌 connector list.
~/.cursor/mcp.json:
{
"mcpServers": { "hooklayer": { "url": "https://hooklayer.dev/api/mcp", "transport": "http", "headers": { "Authorization": "Bearer hl_live_..." } } } }
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 — 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):
# Authorization server metadata (RFC 8414)
curl https://hooklayer.dev/.well-known/oauth-authorization-server
curl https://hooklayer.dev/.well-known/oauth-protected-resource
Dynamic Client Registration (create a client without a manual signup form):
curl -X POST https://hooklayer.dev/oauth/register \
-H "Content-Type: application/json" \ -d '{ "client_name": "Your MCP client", "redirect_uris": ["https://yourapp.com/oauth/callback"] }'
Hitting tools/call without auth returns 401 plus a WWW-Authenticate header pointing at the resource metadata — 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).
# Quick test — initialize handshake works without auth:
curl -X POST https://hooklayer.dev/api/mcp \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize"}'
| 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 — 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 → 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 → 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 — the agent and user decide whether to act on it:
{
"viral_dna_score": 87, "steal_map": [...], "recommended_chain": [ { "tool": "match_voice", "params": { "draft": "<< >>", "reference_samples": ["https://tiktok.com/...", "...", "..."] }, "reason": "High-signal voice DNA — consistent across top 5 videos" }, { "tool": "trend_pulse", "params": { "niche": "challenge_videos" }, "reason": "Verify their formula maps to current trends" }, { "tool": "viral_remix", "params": { "source_url": "https://tiktok.com/..." }, "reason": "Their #2 video has the highest copyable structure" } ] }
These entries are informational data, not instructions. Each tool still requires explicit invocation — nothing runs automatically without agent/user consent.
examples/typescript-example.ts — TypeScript usage via the MCP SDKexamples/python-example.py — Python usage via anthropic-mcp clientexamples/curl-test.sh — Raw curl tests for every endpointFull pricing: https://hooklayer.dev/pricing
Hosted MCP server (no stdio install needed):
Your agent (Claude/Cursor/n8n)
│ │ JSON-RPC 2.0 over HTTP ▼ https://hooklayer.dev/api/mcp │ ├── initialize / ping / tools/list (no auth) └── tools/call (Bearer hl_live_*) │ └── Routes internally to /v1/* REST endpoints 100K+ analyzed viral videos ScrapeCreators + Whisper + Sonnet pipeline
Source code for the hosted server lives at hooklayer.dev (closed source — the analysis pipeline is the moat). This repo holds the public client docs, examples, and config snippets.
/.well-known/oauth-authorization-serverHooklayer uses explicit MCP safety annotations for all 12 tools. Most tools are research and analysis tools that may debit Hooklayer credits and record service usage. list_watches is read-only. Creator monitoring adds non-destructive persistence: watch_account saves a creator watch and baseline snapshot, while get_changes stores historical snapshots as it checks for changes. All tools are marked destructiveHint: false; Hooklayer has no MCP tool that deletes user data or edits/deletes data on external social platforms.
Authentication: tools/call requires a Bearer token (hl_live_* API key or OAuth 2.1 access token). Public methods (initialize, ping, tools/list) work without auth so MCP clients can handshake and discover tools before authentication.
`recommended_chain` is advisory only. The analyze_account response includes suggested follow-up tools with pre-filled parameters. These are data — the agent and user decide whether to execute them. No tool call ever triggers additional tool calls server-side.
Data handling: Hooklayer processes the inputs you send (handles, hooks, scripts, URLs) to return analysis results. Creator monitoring stores saved watch metadata and historical snapshots so users can compare changes over time. Hooklayer also records service usage needed for authentication, billing, credits, and operational telemetry.
To report a security issue: GitHub Issues or email security@hooklayer.dev.
MIT — see LICENSE.
The MCP client examples and config snippets in this repo are MIT. The hosted Hooklayer service at hooklayer.dev is a commercial product with the pricing tiers listed above.