luma-tabs

luma-tabs

MCP server for managing Chrome tabs and tasks, enabling AI agents to search, recall, and organize browser sessions by preventing duplicate tabs, fuzzy searching, and saving workspaces as tasks.

Category
Visit Server

README

Luma Tabs

任务优先的 Chrome 标签管理器:阻止精确重复标签,用最近优先和模糊匹配找回页面,并把长期工作现场保存成可继续的任务。

Luma Tabs 任务工作现场

下载

当前为 0.1.0-beta 测试版,使用 Chrome 开发者模式加载,暂不支持自动更新。

核心能力

  • 重复标签路由:新打开精确重复页面时,自动回到已打开标签。
  • 最近优先搜索:统一搜索已打开、最近关闭、历史、书签和任务资料。
  • 中文模糊召回:支持标题、网址、拼音、首字母、轻微错字和乱序关键词。
  • 任务工作现场:保存核心文档与参考资料,一键恢复并投影为 Chrome 原生标签组。
  • Agent 连接:可选通过本机 Companion 让 Codex、Claude Code 等 MCP Client 操作任务。

只安装 Chrome 扩展

  1. 下载并解压 luma-tabs-0.1.0.zip
  2. 在 Chrome 打开 chrome://extensions
  3. 开启“开发者模式”,点击“加载已解压的扩展程序”。
  4. 选择根目录中含有 manifest.json 的文件夹。
  5. 点击 Luma 图标打开侧边栏。

启用 Agent

Agent 功能需要 Node.js 18 或更高版本。先安装 Chrome 扩展,再下载总包并安装 Companion:

npm install -g "/absolute/path/luma-tabs-agent-0.1.0.tgz"
luma install-host

Codex:

codex mcp add luma-tabs -- luma mcp

Claude Code:

claude mcp add --transport stdio --scope user luma-tabs -- luma mcp

重新加载 Luma,在“更多 -> 设置 -> Agent 连接”中开启“允许 Agent 操作 Luma”,然后重启 Agent。完整步骤见 测试版安装说明

本地开发

npm install
npm run check
npm run test:extension

构建后在 chrome://extensions 加载项目中的 dist 目录。视觉预览可运行:

npm run dev

隐私

Luma 本地处理标签、任务和搜索数据,不读取网页正文,不注入内容脚本,不申请 <all_urls>,也不包含广告或分析 SDK。历史、书签、标签组和 Agent 连接均使用可选权限。详见 隐私说明

反馈

  • 功能问题与建议:提交 Issue
  • 安全问题:使用 GitHub Security Advisory 私下报告,不要公开敏感细节。

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured