Zread MCP Server

Zread.ai MCP Server - 连接 zread.ai 文档平台的 MCP 服务器,让 AI 助手能够阅读 GitHub 仓库文档、搜索代码、与仓库 AI 对话。

Local serverstdioPython

What is the Zread MCP server?

Most developer tooling work still happens through a UI a human drives. Zread MCP server moves it into the conversation instead. Zread.ai MCP Server - 连接 zread.ai 文档平台的 MCP 服务器,让 AI 助手能够阅读 GitHub 仓库文档、搜索代码、与仓库 AI 对话。.

The short version

  1. 访问 https://zread.ai 并登录 2. 按 F12 打开控制台 3. 粘贴运行: javascript prompt('复制token', JSON.parse(localStorage.getItem('CGX_AUTH_STORAGE')).state.token) 4. 复制弹窗中的 Token

Getting it running

zread-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 9 tools. What each one is for:

  • fetch_documentation_page — 否
  • search_documentation — 否
  • get_documentation_outline — 否
  • discover_repositories — 否
  • find_repositories — 否
  • get_trending_repositories — 否
  • check_repository_status — 否
  • ask_repo_ai
  • fetch_repository_file

What it needs from you

Configuration is passed through the environment: ZREAD_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Zread.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Zread's toolset — fetch_documentation_page, search_documentation, get_documentation_outline and 6 more — is a fair guide to whether it matches your workflow. It is maintained by ejfkdev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
fetch_documentation_page
search_documentation
get_documentation_outline
discover_repositories
find_repositories
get_trending_repositories
check_repository_status
ask_repo_ai**是**
fetch_repository_file**是**

How to install the Zread MCP server

## MCP 客户端配置

### npx(Node.js)
```json
{
  "mcpServers": {
    "zread": {
      "command": "npx",
      "args": ["-y", "zread-mcp-server"],
      "env": {
        "ZREAD_TOKEN": "your-token"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
ZREAD_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Zread to fetch documentation page.
  • Use Zread to search documentation.
  • Use Zread to get documentation outline.

Frequently asked questions

It connects Zread to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (fetch_documentation_page, search_documentation, get_documentation_outline, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Zread directly.