# ReadGZH

A hosted MCP server that pulls the full body of public WeChat Official Account articles and hands your agent clean Markdown.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: sweesama
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sweesama/readgzh
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/readgzh

## What it does

Give ReadGZH a link like `https://mp.weixin.qq.com/s/...` and it comes back with the title, the author, the publish time and the article body as Markdown. Standard posts and image-post (图文) pages both work. Nothing runs on your machine — no WeChat desktop client, no scraping script to babysit.

The MCP side exposes five tools. `readgzh.read` extracts an article from a URL, `readgzh.search` looks through cached posts by keyword, `readgzh.list` and `readgzh.list_by_account` show what was read recently, and `readgzh.get` fetches a cached article by slug. Search and listing cover the ReadGZH cache only, so this is not a full WeChat index. A fresh read costs 3 credits; reading something already cached costs nothing.

Two endpoints exist. The OAuth one at `https://jhnnmmwgdrquwjytvvwu.supabase.co/functions/v1/mcp` sends you through a sign-in and consent page. The API-key one at `https://api.readgzh.site/mcp-server` takes the key in the `Authorization` header, and anonymous calls share an IP-based quota. You need a key from the dashboard before the first fetch of a new article, or the request fails. Anything you submit lands in a shared cache, so keep material you would not want cached out of it.

## Requirements
- Remote server: `https://api.readgzh.site/mcp-server`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http readgzh https://api.readgzh.site/mcp-server
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add readgzh --url https://api.readgzh.site/mcp-server
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "readgzh": {
            "url": "https://api.readgzh.site/mcp-server"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "readgzh": {
            "type": "http",
            "url": "https://api.readgzh.site/mcp-server"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http readgzh https://api.readgzh.site/mcp-server
```

## When to use it
- get the article body your agent cannot open on its own
- keep the title, author and publish date attached to the text
- shrink a long article before it hits the context window
- find a post you read earlier by keyword
- line up several articles side by side in one prompt

## Example prompts
- Read this and summarise the main points: https://mp.weixin.qq.com/s/xxxx
- Search the cache for posts about MCP servers and list the titles
- Fetch the article by slug and list every tool it mentions

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md