Google Workspace (multi-account)

io.github.bakissation由 GitHub 账号 bakissation 发布v6.2.0更新于 Nov 4, 2026

Multi-account Google Workspace MCP server: 944 tools, 29 services, discover-first, BYO OAuth.

概览

AI 生成的概览

本地 MCP 服务器,把 Gmail、Drive、日历、表格、文档等 Google Workspace API 作为工具开放,并支持多个 Google 账号。

可以做什么
  • 以 Markdown 读取、发送和回复 Gmail 邮件,支持附件
  • 操作 Drive 文件、Docs、Sheets、Slides、Forms 和通讯录
  • 管理日历事件、Tasks、Chat、Meet 和 Classroom
  • 查询 Analytics(GA4)与 Search Console 数据
  • 管理 Vault 与 Admin 服务,并为其他 API 方法提供通用入口
  • 按别名切换账号,或把一次调用分发到所有账号
适用场景
适合让助手直接在你的 Google 账号里工作:整理邮件、起草回复、读取或编辑文档与表格、查看日历、拉取分析数据;需要同时使用多个 Google 账号时尤其有用。
运行要求
通过 npx 以 stdio 在本地运行(需 Node.js 22 或更高版本),也可作为 Claude Desktop 扩展包安装。需要自建 Google Cloud OAuth 桌面客户端:GOOGLE_CLIENT_ID、GOOGLE_CLIENT_SECRET,以及列出别名与邮箱的 GOOGLE_ACCOUNTS。每个账号需在浏览器中登录授权;MASTER_KEY 未设置时会自动生成。
安装前请注意
需要你自己的 Google OAuth 客户端凭据,并授予服务器访问 Google 数据的权限;令牌在本地加密存储。写入默认被拒绝,但可开启,因此可能发送邮件、修改或删除内容。服务器只与 Google 通信,但客户端密钥与主密钥须妥善保管。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Google Workspace (multi-account),将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

mcp-google-multi

The most complete local Google Workspace MCP server: Gmail, Drive, Calendar, Sheets, Docs, Slides, Forms, Contacts, Tasks, Chat, Meet, Analytics (GA4), Search Console, Classroom, Vault, Admin and more — every OAuth-reachable API method as a tool, across multiple Google accounts at once, from Claude Code or any MCP client.

[npm]

  • 🧰 Exhaustive — 944 tools across 29 services, now including Google Analytics (GA4), + an escape hatch for anything else → COVERAGE.md
  • 🔑 Multi-account — drive any number of Google accounts by alias, or fan one call out across all of them
  • 🔒 Private by design — your own OAuth app, tokens encrypted at rest (AES-256-GCM), writes deny-by-default, no telemetry, no metering — it talks only to Google
  • 🌐 Local or remote — runs locally over stdio, or self-hosted over HTTP with its own built-in OAuth 2.1 server (Claude Code's /mcp login and the claude.ai connector, zero custom UI). Pull-and-up Docker Compose with optional automatic HTTPS → remote setup
  • ✉️ Built for real work — send and read email in Markdown with attachments and one-call replies, an interactive setup wizard with a doctor self-check, and per-account scope profiles → features tour

Quick setup

New to all this? It's written for someone who just installed Claude Code and has never made an API key. Copy-paste each step; it says what you'll see. (Already technical? The Configuration reference is the terse version.)

  1. Install it. Get Node.js (the green "LTS" button, version 22 or newer), then run:

    bash
    npm install -g mcp-google-multi

    Claude Desktop user? You can skip npm entirely: download the mcp-google-multi.mcpb bundle from the latest release, double-click it (or drag it into Claude Desktop → Settings → Extensions), and fill in the values from step 2 when prompted.

  2. Make your Google key (the one manual part, a few minutes, because Google has no way to script it). Follow the step-by-step Google Cloud setup, or just ask Claude Code: "walk me through creating a Google OAuth Desktop client for mcp-google-multi." You finish with two values, a Client ID and a Client Secret. It's free and private to you.

  3. Put them in a file. In the folder you'll run from, make a file named .env and paste this, filling in your values:

    bash
    GOOGLE_CLIENT_ID=paste-your-client-idGOOGLE_CLIENT_SECRET=paste-your-client-secret# any short nickname, then your Gmail address:GOOGLE_ACCOUNTS=me:[email protected]

    No encryption key to make: the server generates and stores one for you.

  4. Sign in. A browser opens; pick your account and click Allow:

    bash
    mcp-google-multi auth --account me
  5. Add it to Claude Code, then restart Claude Code:

    bash
    claude mcp add mcp-google-multi -s user -- npx -y mcp-google-multi

Stuck at any point? Run mcp-google-multi doctor. It inspects every part and prints the exact fix for anything wrong (a missing sign-in, a Google API you still need to switch on, and so on). Once it reads all-green, just talk to Claude: "summarize my unread email."

Got more than one Google account? Add them together, like GOOGLE_ACCOUNTS=me:[email protected],work:[email protected], and run step 4 once per nickname.

On a server or from claude.ai? Advanced path: Remote / HTTP setup. Coming from v5? v6 migration guide.

Go deeper: Configuration reference · What's covered · Features tour · Remote / HTTP setup · Secrets in a vault · Local usage metrics · Migrating to v6 · Security policy · Roadmap

Agent skill

The repo and the npm package both ship an Agent Skill at skills/google-workspace/: a hand-written SKILL.md covering account selection, the discover step, incremental Gmail sweeps, keeping results small, write profiles, and the escape hatch, plus a reference/ folder with a generated argument table per service. Loading it gets an agent calling this server's tools correctly without guessing argument names.

To install it for Claude Code, copy or symlink the skills/google-workspace folder into ~/.claude/skills/ (every project) or a project's own .claude/skills/ (that project only):

bash
# from a cloned copy of this repoln -s "$(pwd)/skills/google-workspace" ~/.claude/skills/google-workspace
# from the installed npm packageln -s "$(npm root -g)/mcp-google-multi/skills/google-workspace" ~/.claude/skills/google-workspace

Maintainer, sponsor & license

Built and maintained by Abdelbaki Berkati — berkati.xyz · @bakissation. Read the case study →

Development is funded by IdeaCrafters (@IdeaCraftersHQ) — the studio that pays for this OSS to exist.

An Enterprise Edition (hosted, multi-tenant) is available: ask through berkati.xyz (email or LinkedIn there).

Thanks to contributors @obatried, @trevor-commits, and @mjreddy. The project is maintainer-led (roadmap on Milestones; bug reports welcome, feature PRs by prior agreement — see CONTRIBUTING.md). Feedback shapes the roadmap: open an issue with bugs, pain points, or what you wish it did. Security reports go to SECURITY.md, never a public issue.

Licensed under MIT.

来源:README.md,提交 45842e2

工具

0
SourceWeft 曾在隔离沙箱中以无凭据方式启动该软件包一次,以列出其工具,但未能完成:服务器未能启动。

版本历史

5
  1. v6.2.0最新Nov 4, 2026
  2. v6.1.1Oct 26, 2026
  3. v6.1.0Oct 20, 2026
  4. v6.0.1Oct 18, 2026
  5. v6.0.0Oct 14, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分