Zread Mcp

io.github.ejfkdevPublished by GitHub account ejfkdevv1.0.1Updated Oct 27, 2026

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。

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Connects an assistant to the Zread.ai documentation platform to read GitHub repository docs, search code repositories and ask a repo AI questions.

What you can do
  • Fetch, search and outline documentation pages for GitHub repositories
  • Discover recommended repositories, search repositories and list trending repositories
  • Check the status of a repository
  • Ask the repository AI assistant questions (requires token)
  • Read source code files from a repository (requires token)
When to use it
Useful when you want an assistant to research open-source repositories: reading their documentation, finding relevant projects, or asking questions about a specific codebase without cloning it locally.
Requirements
Runs locally via npx (Node.js) or uvx (Python); stdio by default, with optional HTTP/SSE mode on a host and port. A ZREAD_TOKEN environment variable is needed for the AI Q&A and file-fetch tools; the other tools work without it. Network access to zread.ai is required.
Before you install
The token is a Zread.ai account credential; the README suggests extracting it from the site's browser localStorage, so treat it as sensitive and pass it only via the ZREAD_TOKEN environment variable. Tools that ask the repo AI or fetch source files send requests to the third-party zread.ai service. HTTP mode binds to 127.0.0.1 by default; exposing it on another host would widen access.

Installation

In SourceWeft

  1. Open Zread Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Zread.ai MCP Server

[Python] [Node.js] [MCP] [License]

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。

💡 提示 AI：这是一个 MCP (Model Context Protocol) 服务器，提供 9 个工具用于代码仓库分析。支持 Python 和 Node.js 两种实现，可通过 npx 或 uvx 一行命令运行。核心功能包括文档查询、仓库搜索、AI 问答。

功能

  • 文档查询 - 获取仓库文档页面、目录结构、搜索关键词
  • 仓库发现 - 推荐仓库、热门榜单、搜索代码库
  • AI 问答 - 向仓库 AI 助手提问（需 Token）
  • 文件获取 - 读取源代码文件内容（需 Token）

快速启动

bash
uvx zread-mcpnpx zread-mcp

带 Token 运行

bash
# uvx (Python)uvx --env ZREAD_TOKEN=your-token zread-mcp
# npx (Node.js) - Windowsset ZREAD_TOKEN=your-token && npx zread-mcp
# npx (Node.js) - macOS/LinuxZREAD_TOKEN=your-token npx zread-mcp

HTTP 模式 (Streamable HTTP)

bash
uvx zread-mcp --transport http --port 3000npx zread-mcp --transport http --port 3000

更多运行方式

Python 生态

bash
# uvx 从 PyPI 运行（推荐）uvx zread-mcp
# uvx 从 GitHub 仓库运行uvx --from git+https://github.com/ejfkdev/zread-mcp.git zread-mcp
# uv 运行远程脚本uv run https://raw.githubusercontent.com/ejfkdev/zread-mcp/main/zread_mcp_server.py
# pipx 从 GitHub 运行pipx run --spec git+https://github.com/ejfkdev/zread-mcp.git zread-mcp
# pipx 安装到本地pipx install git+https://github.com/ejfkdev/zread-mcp.gitzread-mcp --transport http
# 本地运行python zread_mcp_server.py

Node.js 生态

bash
# pnpmpnpm dlx ejfkdev/zread-mcp
# bunbunx ejfkdev/zread-mcp
# 全局安装npm install -g ejfkdev/zread-mcpzread-mcp-server --transport http

MCP 客户端配置

npx（Node.js）

json
{  "mcpServers": {    "zread": {      "command": "npx",      "args": ["-y", "zread-mcp-server"],      "env": {        "ZREAD_TOKEN": "your-token"      }    }  }}

uvx（Python）

json
{  "mcpServers": {    "zread": {      "command": "uvx",      "args": ["--env", "ZREAD_TOKEN=your-token", "zread-mcp"]    }  }}

获取 Token

部分高级功能（AI 问答、文件获取）需要 ZREAD_TOKEN：

  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

命令行参数

--transport {stdio,http,sse}  传输协议 (默认: stdio, http/sse 等价)--host HOST                   HTTP 模式主机 (默认: 127.0.0.1)--port PORT                   HTTP 模式端口 (默认: 3000)--token TOKEN                 ZREAD_TOKEN--no-token                    强制无 Token 模式-h, --help                    显示帮助

工具列表

工具需要 Token说明
fetch_documentation_page否获取文档页面
search_documentation否搜索文档
get_documentation_outline否获取文档大纲
discover_repositories否发现推荐仓库
find_repositories否搜索仓库
get_trending_repositories否热门仓库榜单
check_repository_status否检查仓库状态
ask_repo_ai是AI 智能问答
fetch_repository_file是获取源代码文件

开发

bash
# 克隆仓库git clone https://github.com/ejfkdev/zread-mcp.gitcd zread-mcp
# Python 测试python zread_mcp_server.py --test
# Node.js 测试node zread-mcp-server.js --test

许可证

MIT License

Source: README.md at commit 7be9e90

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts