Connects Claude to Zread.ai, a documentation platform for GitHub repositories. You get nine tools split between public operations (fetch docs pages, search documentation, discover trending repos, check repository status) and token-gated features (ask the repository AI assistant questions, fetch raw source files). The public tools are useful for browsing indexed repos and their generated documentation. The AI chat and file access require grabbing a token from Zread.ai's localStorage after logging in. Ships as both Python and Node.js implementations, runnable via uvx or npx without installation. Reach for this when you want Claude to navigate repository documentation or query Zread's AI summaries of codebases instead of hitting GitHub's API directly.
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。
uvx zread-mcp
npx zread-mcp
# uvx (Python)
uvx --env ZREAD_TOKEN=your-token zread-mcp
# npx (Node.js) - Windows
set ZREAD_TOKEN=your-token && npx zread-mcp
# npx (Node.js) - macOS/Linux
ZREAD_TOKEN=your-token npx zread-mcp
uvx zread-mcp --transport http --port 3000
npx zread-mcp --transport http --port 3000
# 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.git
zread-mcp --transport http
# 本地运行
python zread_mcp_server.py
# pnpm
pnpm dlx ejfkdev/zread-mcp
# bun
bunx ejfkdev/zread-mcp
# 全局安装
npm install -g ejfkdev/zread-mcp
zread-mcp-server --transport http
{
"mcpServers": {
"zread": {
"command": "npx",
"args": ["-y", "zread-mcp-server"],
"env": {
"ZREAD_TOKEN": "your-token"
}
}
}
}
{
"mcpServers": {
"zread": {
"command": "uvx",
"args": ["--env", "ZREAD_TOKEN=your-token", "zread-mcp"]
}
}
}
部分高级功能(AI 问答、文件获取)需要 ZREAD_TOKEN:
prompt('复制token', JSON.parse(localStorage.getItem('CGX_AUTH_STORAGE')).state.token)
--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 | 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 |
# 克隆仓库
git clone https://github.com/ejfkdev/zread-mcp.git
cd zread-mcp
# Python 测试
python zread_mcp_server.py --test
# Node.js 测试
node zread-mcp-server.js --test
MIT License
ZREAD_TOKENsecretYour API key for the service
ray0907/git-mcp-server
cyanheads/git-mcp-server
io.github.b1ff/atlassian-dc-mcp-bitbucket
io.github.b1ff/atlassian-dc-mcp-jira
com.mcparmory/atlassian-jira
sirlordt/vscode-terminal-mcp