readgzh
Read full-text WeChat Official Account articles, returning title, author, publish time, and clean Markdown content, with support for standard articles and image-post formats. Also provides search and listing of cached articles.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@readgzhRead this WeChat article: https://mp.weixin.qq.com/s/abc123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ReadGZH — WeChat Article Reader for AI
Let AI read full-text WeChat Official Account (微信公众号) articles. Cloud-based, zero-install. Returns title, author, publish time, and clean Markdown content. Supports standard articles and image-post (图文) formats.
🌐 Site: https://readgzh.site
📖 Docs: https://readgzh.site/docs
💳 Pricing: https://readgzh.site/pricing
🔑 Dashboard / API Key: https://readgzh.site/dashboard
Why ReadGZH
WeChat articles can't be read by Claude, ChatGPT, Cursor, or other AI tools — mp.weixin.qq.com blocks bots. ReadGZH solves this with a cloud reader you can call from any AI client.
☁️ Cloud-based — no WeChat desktop install, no local script
💰 Shared cache — previously read articles cost 0 credits for everyone
🖼️ CDN image proxy — permanent image links, no expiry
📱 Image-post (图文) support — full coverage of WeChat's gallery format
🤖 AI summaries — structured JSON via
?mode=summary(Pro)🔌 MCP, OpenAPI, REST — works with Claude Desktop, Cursor, ChatGPT, custom agents
Related MCP server: WeChat Article Parser
Quick Start
Use it from your AI client (MCP)
ReadGZH is a remote MCP server — no install. Add to your MCP client config:
{
"mcpServers": {
"readgzh": {
"url": "https://api.readgzh.site/mcp-server"
}
}
}Then ask your AI: "Read this for me: https://mp.weixin.qq.com/s/..."
Optional API key (higher quota, bypasses anonymous IP limits):
{
"mcpServers": {
"readgzh": {
"url": "https://api.readgzh.site/mcp-server",
"headers": { "Authorization": "Bearer rgz_..." }
}
}
}Use it from code (REST)
curl -X POST https://api.readgzh.site/rd \
-H "Content-Type: application/json" \
-H "Authorization: Bearer rgz_..." \
-d '{"url":"https://mp.weixin.qq.com/s/xxxx"}'Full API spec: https://readgzh.site/.well-known/openapi.yaml
Tools (MCP)
Tool | Purpose |
| Read & extract a WeChat article from a URL |
| Search cached articles by keyword |
| List recently cached articles |
| Fetch a cached article by slug |
Pricing
Free — 30 credits/day for registered users · 10/IP/day anonymous
Lite — ¥9/month · 300 reads/month
Pro — ¥39/month · 2000 reads/month + AI summary
Each fresh read = 3 credits. Cached re-reads = 0. Details: https://readgzh.site/pricing
Tech Stack
React 18 + Vite + TypeScript + Tailwind + shadcn/ui
Lovable Cloud (Supabase: Postgres, Auth, Edge Functions, Storage)
Cloudflare Worker proxy (
api.readgzh.site)Stripe subscriptions
MCP via
mcp-lite
License
AGPL-3.0. If you self-host or fork ReadGZH as a network service, you must release your modifications under the same license. For commercial licensing without AGPL obligations, contact support@readgzh.site.
Contact
Support: support@readgzh.site
Issues: GitHub Issues
Built with ❤️ on Lovable
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceEnables parsing and extracting content from WeChat public account articles using browser simulation, supporting multiple output formats (JSON, Markdown, HTML) and media resource extraction.Last updated
- Flicense-qualityDmaintenanceParses WeChat public account articles to extract metadata, content, and generate AI-powered summaries with semantic analysis, viewpoint extraction, and structure analysis capabilities.Last updated
- Flicense-qualityDmaintenanceEnables fetching, searching, and summarizing WeChat public account articles through browser automation. Supports multiple output formats and provides article metadata and statistics.Last updated1
- Alicense-qualityDmaintenanceEnables reading and extracting content from WeChat public account articles using browser automation, allowing AI models to analyze and summarize WeChat articles through natural language requests.Last updated440MIT
Related MCP Connectors
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Fetch any URL and get clean Markdown. Web scraping for AI agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sweesama/readgzh'
If you have feedback or need assistance with the MCP directory API, please join our Discord server