ReadGZH
Officially listedA converter that turns WeChat official account articles into AI-readable text and Markdown.
ReadGZH
ReadGZH is an online service that converts WeChat official account articles into AI-readable formats. WeChat official accounts tightly restrict external requests — ChatGPT, Claude, and DeepSeek requesting mp.weixin.qq.com directly often can't get the article body — so it fetches and cleans via a server-side proxy, outputting pure text with zero JS dependencies, built for researchers and developers who need to feed official account long-forms to AI.
Core capabilities
- MCP Server: built-in remote MCP with 5 tools (read/list/search, etc.), letting agents fetch article bodies with zero installation
- REST API: GET /rd?url=<article link> returns the body directly, with format=text for Markdown and part=N chunking
- Server-side cleaning: strips inline style/class/data-* attributes, removes WeChat-private tags, and collapses empty tags, outputting clean SSR HTML
- Shared cache: cache hits read at 0 credits, with long articles auto-chunked at roughly 40KB
- Image proxy: forwards WeChat images through a CDN, easing expired original-image links
- AI summaries: Pro users can generate structured summaries with mode=summary
Use cases Feeding official account long-forms to ChatGPT/Claude/DeepSeek for summarization, translation, and comparison; developers building "WeChat article → Markdown" data pipelines for agents/RAG; enterprises needing shared quotas and invoices for content analysis.
Unique advantages Where Jina Reader frequently returns 403 on WeChat official accounts, ReadGZH specializes vertically in anti-scraping penetration; versus open-source solutions requiring local deployment, it is cloud-hosted, zero-install infrastructure with shared caching and image proxying.
Editorial verdict Both the API and MCP tested live in this review; the free 30 credits daily is a friendly threshold and Lite starts at ¥9/month — few one-stop alternatives exist for this "WeChat content → AI" need. Caveats: the operator is an anonymous indie developer with no company entity or ICP filing; the public "article library" indexing others' articles raises copyright disputes (the site offers a takedown channel and disclaimers); key metrics are self-reported with no third-party reviews. Respect original authors' copyrights and don't process private content.
Pricing
### 💰 定价模式：免费增值（积分制） **起步价**：免费（每日 30 积分） #### 主要方案 - **Free**：¥0 - 每日手动领取 30 积分，缓存读取免费 - **Lite**：¥9/月 - 每月 300 积分，用量面板，缓存免费 - **Pro**：¥39/月 或 ¥299/年 - 每月 2,000 积分，含 AI 摘要与优先抓取队列 - **加量包**：¥9–15/份 - 每份 500 积分，自购买起 30 天有效 - **企业版**：¥1,380–9,800/年 - 团队共享积分池（3,000–40,000 积分/月），可开票对公 #### 试用/其他信息 首次抓取 3 积分/篇，命中共享缓存不扣积分；匿名每 IP 每天 10 积分；提供 14 天自助退款。 — Visit website
FAQ
Is ReadGZH free?
There is a free tier: claim 30 credits daily by hand (about 10 articles), and cache-hit article reads cost no credits; paid starts at Lite ¥9/month, plus ¥39/month Pro and an enterprise tier.
What is ReadGZH used for?
Converts WeChat official account articles into AI-readable plain text or Markdown for feeding to ChatGPT, Claude, and DeepSeek for summarization, translation, comparison, and note-taking, or integrating into programs via API.
Does ReadGZH support the MCP protocol?
Yes. A built-in remote MCP Server (api.readgzh.site/mcp-server) tested working in this review, providing 5 tools — read, list, search, list_by_account, get — that agents can use with zero installation.
How does ReadGZH differ from Jina Reader?
Jina Reader is more general with a larger free allowance but often returns 403 on WeChat official accounts; ReadGZH specializes vertically in WeChat anti-scraping penetration and additionally offers shared caching, image proxying, and long-article chunking.
How is ReadGZH billed?
Credit-based: fetching a first-time uncached article costs 3 credits, cache hits cost 0; subscription plans grant monthly credits, and a 500-credit top-up pack is valid for 30 days from purchase.
Can ReadGZH read paywalled or deleted articles?
No. It only supports publicly accessible articles — deleted, video-only, or authorization-required articles error out; its "article library" search also covers only processed articles, not all of WeChat.
Are converted article links public?
Yes. Converted pages are publicly accessible and may also appear in the site's "article library" for others to find, so don't use it for private, internal, or unauthorized content.