Earlywire — Marketing & Growth Intelligence

** Earlywire — Marketing & Growth Intelligence is the marketing & growth wire for AI assistants. It reads 120+ curated practitioner sources every morning — newsletters, vendor changelogs, and the SEO, analytics and paid-media feeds that matter — and scores each piece 0–10 for signal (only score ≥7 is served). Your assistant gets fresh, judged items with a citable own-words summary and a link to the source, instead of whatever ranks on web search. Use it alongside web search, not instead of it. **Connect (Claude Code):** `claude mcp add --transport http earlywire https://earlywire.barisasa.com/mcp` **Add the skill (so it actually fires):** The skill tells Claude to consult Earlywire — alongside web search — for marketing questions, so it gets used instead of defaulting to the open web. `/plugin marketplace add barisasaa/earlywire then /plugin install earlywire-marketing` (installs the skill and the connector in one step). claude.ai / Desktop: full two-step setup at https://earlywire.barisasa.com/setup Free, no key, 30 requests/minute. **Tools** - `earlywire_search` — full-text search across the corpus - `earlywire_topic_pulse` — what the niche is saying: volume, sources, score spread, top takes - `earlywire_whats_new` — newest judged items, by category - `earlywire_trending` — topics rising vs the prior window - `earlywire_get_item` — one item's summary + excerpt + source link - `earlywire_coverage` — sources, freshness, category mix Own-words summary + short excerpt, always linked to source. Covers marketing, growth, analytics, paid media, SEO and AI search — plus the AI shifts reshaping them.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://earlywire--hello-lc0b.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Earlywire — Marketing \u0026 Growth Intelligence": {
      "url": "https://earlywire--hello-lc0b.run.tools"
    }
  }
}

能力清单

工具	说明
whats_new	Newest items on the wire — judged atoms from marketing/growth newsletters, vendor changelogs, and practitioner feeds. Args: category (one of 15 slugs, e.g. 'marketing-analytics', 'paid-ads', 'seo', 'ai-models'; omit for all), since_days (default 7), min_score (judge score floor 0-10, default 6), limit (default 20).
search	Full-text search across titles, tldrs, topics, and excerpts of the corpus. Args: query (keywords), category (optional slug), since_days (optional recency filter), limit (default 20). Relevance-ranked. For specifics beyond the excerpt, FETCH the item's url — most are public pages.
topic_pulse	What the marketing/growth niche is saying about a topic: chatter volume, who covers it, score spread, top takes. Args: topic (free text, e.g. 'consent mode', 'AI Max'), since_days (default 30). Use to gauge discussion and disagreement, not just list items.
trending	Topics rising this window vs the previous one (mention velocity over judge topic tags). Args: window_days (default 7).
get_item	Fetch one item by id: tldr, judge reason, and a short excerpt. This wire serves excerpts only — for full specifics (numbers, claims, recommendations) FETCH the source url with your web tools before synthesizing; most sources are public pages.
coverage	What this wire does and doesn't cover: per-source freshness and volume, category mix, last refresh. Call when unsure whether a question is answerable from here. The corpus is a curated marketing/growth niche (incl. the AI shifts affecting it) — not general news.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。