ReadGZH MCP Server

by sweesama Your server? Claim it

answering

ReadGZH is answering right now. Last checked 52 min ago. It exposes 5 tools. Last commit 27 Oct 2026.

Read WeChat public account articles via MCP. 99.89% anti-scraping success, 50-87% token compression.

Uptime history 91 days of history · worst day 0%

91 days agonow

100.0%

Uptime 24h

88 of 88 checks

Tools

read from the server

555 ms

Response time

average over 24h

Stars

last commit 27 Oct 2026

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 14 August 2026. No other catalogue keeps this.

14 Aug a tool appeared readgzh.list_by_account

Nothing serious here today

Today is the operative word: we check ReadGZH every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 52 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add readgzh --transport http https://api.readgzh.site/mcp-server

Settings → Connectors → Add custom connector, then paste this address

https://api.readgzh.site/mcp-server

~/.codex/config.toml

[mcp_servers.readgzh]
url = "https://api.readgzh.site/mcp-server"

.cursor/mcp.json

{
  "mcpServers": {
    "readgzh": {
      "url": "https://api.readgzh.site/mcp-server"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "readgzh": {
      "type": "http",
      "url": "https://api.readgzh.site/mcp-server"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

readgzh

readgzh.get

Get a cached WeChat article by its short slug/URL path via ReadGZH. Use when you have a slug like 'minicpm-o-4-5' from a previous read.

readgzh.list

List recently cached WeChat articles via ReadGZH. Returns titles, authors, and links. Useful for browsing what articles have been previously read and cached.

readgzh.list_by_account

List cached WeChat articles published by one Official Account (公众号) via ReadGZH. IMPORTANT: this only covers articles already cached by ReadGZH — WeChat has no public API for a full account archive, so the result is not exhaustive. Use it to find other articles by the same author after reading one.

readgzh.read

Read and extract the full text content of a WeChat Official Account (微信公众号) article via ReadGZH (readgzh.site). Provide a WeChat article URL and get back the title, author, publish time, and full article text in Markdown format. The article will be automatically cached for future reads.

readgzh.search

Search cached WeChat articles by keyword via ReadGZH. Searches in article titles and content. Returns matching articles with snippets.

Endpoints

URL	Transport	State	Latency	Checked
https://api.readgzh.site/mcp-server	streamable-http	answering	482 ms	52 min ago

Alternatives to ReadGZH

same job, measured the same way

Robot Resources Scraper

by robot-resources

Token compression for web content — 70-80% reduction from HTML to clean markdown

39 installs/wk local only

Scrapingant

by pipeworx-io

ScrapingAnt MCP — wraps the ScrapingAnt web scraping API (scrapingant.com)

213 installs/wk 47 tools answering

Scrapingbee

by pipeworx-io

ScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)

203 installs/wk 47 tools answering

Research

by ilo415

AI research for agents. Company intel, competitor analysis, web scraping, topic dives. Pay via MPP.

45 installs/wk local only

Telegram Channel Scraper

by brenton-keller

Public Telegram channel posts, views, reactions, media and subscriber counts. No login needed.

answering

Telegram Channel Scraper

by bkeller-research

Public Telegram channel posts, views, reactions, media and subscriber counts. No login needed.

answering

readfetch

by readfetch

Stdio MCP: free probe; paid web reading (text/map/scrape) via x402 on readfetch.com

local only

Scrapingant

by scrapingant

Cloud-based web access with real browsers and JS rendering by ScrapingAnt

3 tools answering

ReadGZH — questions

Answers built from our own checks of this server.

What can ReadGZH do?

It exposes 5 tools, read directly from the server on our last check. Among them: readgzh.get, readgzh.list, readgzh.list_by_account, readgzh.read, readgzh.search. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ReadGZH working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 88 of 88 checks got a reply (100.0%), average response time 555 ms. The bar chart above shows every period we have measured.

How do I connect ReadGZH?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ReadGZH need an API key?

No. ReadGZH completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ReadGZH?

It answers our handshake in 555 ms on average, which is faster than 21% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is ReadGZH open source?

The code is open source: it is published under the AGPL-3.0 licence, written in TypeScript and 6 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.readgzh.site, which runs on its operator's own terms.