readgzh

name	readgzh
description	ReadGZH — Let AI read full-text WeChat Official Account articles. Supports standard articles and image-post formats.
version	1.3.0
author	readgzh
triggers	["wechat","weixin","mp.weixin","read article","readgzh","gongzhonghao"]
tools	[{"name":"readgzh.read","description":"Read the full text of a WeChat Official Account article via ReadGZH, returning title, author, publish time, and content","parameters":{"url":"[Truncated]","format":"[Truncated]"}},{"name":"readgzh.search","description":"Search cached WeChat articles by keyword via ReadGZH","parameters":{"query":"[Truncated]","limit":"[Truncated]"}},{"name":"readgzh.list","description":"List recently cached WeChat articles via ReadGZH","parameters":{"limit":"[Truncated]"}},{"name":"readgzh.get","description":"Get a cached article by slug via ReadGZH. Long articles are auto-chunked (~40KB/chunk); use 'part' to paginate","parameters":{"slug":"[Truncated]","part":"[Truncated]","mode":"[Truncated]","format":"[Truncated]"}}]
config	{"api_key":{"type":"string","required":false,"description":"ReadGZH API Key (sk_live_...). Get one free at https://readgzh.site/dashboard. Without a key, the public endpoint is used (rate-limited)."}}

ReadGZH — WeChat Article AI Reader

Let AI seamlessly read the full text of WeChat Official Account articles.

How It Works

When a user shares a WeChat article link (mp.weixin.qq.com), use the readgzh.read tool to call the ReadGZH service. ReadGZH will automatically:

1. Scrape and parse the article content
2. Extract the title, author, publish time, and body text
3. Cache the result for future zero-cost access
4. Return clean, AI-friendly formatted text

Key Features

• Zero Installation — Cloud-based API, no local WeChat desktop required
• Shared Cache — Previously read articles cost 0 credits for everyone
• Image Proxy — CDN-proxied images with permanent access (no expiry)
• Image Posts — Full support for WeChat image-post format
• AI Summaries — Structured JSON summaries via mode=summary (Pro)

Usage Examples

Read an article

User: "Read this article for me https://mp.weixin.qq.com/s/xxxxx" → Call readgzh.read with the URL

Read an article (plain text mode, recommended)

User: "Read this article https://mp.weixin.qq.com/s/xxxxx" → GET /rd?url={URL}&format=text — returns plain Markdown, saves tokens

Search articles

User: "Search WeChat articles about AI" → Call readgzh.search, query = "AI"

Browse recent articles

User: "What articles are available recently?" → Call readgzh.list

Get article by slug

User: "Read the article minicpm-o-4-5" → Call readgzh.get, slug = "minicpm-o-4-5"

API Endpoints

All tools call the ReadGZH API (https://api.readgzh.site):

• Read article: GET /rd?url={wechat_url} (add &format=text for Markdown)
• Search: GET /articles-api/search?q={query}&limit={n}
• List recent: GET /articles-api/recent?limit={n}
• Get by slug: GET /rd?s={slug} (add &part=1 for chunked reading; for Markdown)