Google Workspace Code MCP
A code-first MCP server that provides a single tool to execute JavaScript or TypeScript with authenticated access to Google Workspace APIs. It enables flexible interactions with services like Calendar and Drive by running user-provided scripts through a built-in runtime environment.
README
Google Workspace Code MCP
Important: This is an alternative experiment, not my primary setup
If you are looking for the Google Workspace integration I actually use day-to-day, use this skill instead:
- Primary skill: https://github.com/mitsuhiko/agent-stuff/tree/main/skills/google-workspace
This repository is an alternative code-first MCP experiment built around one execute tool.
It is intentionally aligned with the ideas in:
- Your MCP Doesn’t Need 30 Tools: It Needs Code — https://lucumr.pocoo.org/2025/8/18/code-mcps/
That post explores code-supported/code-first MCP design (fewer fixed tools, more programmable capability).
A local JavaScript/TypeScript MCP server with a single tool: execute.
execute runs JavaScript (or TypeScript with type stripping) and gives that code authenticated access to Google Workspace APIs.
What this server does
- Exposes one MCP tool:
execute - Runs user-provided JavaScript/TypeScript (async function body; TS types stripped)
- Automatically performs OAuth login on first use (browser flow)
- Reuses stored tokens on subsequent calls
- Provides a small runtime API inside executed code:
auth— Google OAuth clientgoogle—googleapisSDK rootworkspace— helper methods (call,service,whoAmI)state— persistent mutable object across calls
This follows a code-mode design: one flexible execution tool instead of many fixed tools.
Requirements
- Node.js 20+
- Local desktop/browser access for the initial OAuth sign-in
Install
npm install
Run
npm start
or:
node src/server.js
MCP configuration
This repo already includes .mcp.json:
{
"mcpServers": {
"google-workspace-code": {
"type": "stdio",
"command": "node",
"args": [
"/Users/mitsuhiko/Development/workspace-mcp/src/server.js"
],
"env": {
"GOOGLE_WORKSPACE_AUTH_MODE": "cloud"
}
}
}
}
If you move the project, update the args path.
Tool contract
Tool name
execute
Input schema
script(string, required): JavaScript/TypeScript async function body (TS type syntax is stripped before execution)timeoutMs(number, optional): execution timeout in milliseconds (default30000, max300000)scopes(string[], optional): override OAuth scopes for the callresetState(boolean, optional): clears persistentstatebefore execution
Execution environment
Your script runs as an async function body with these variables in scope:
authgoogleworkspacestate
Return values are serialized and sent back as tool output.
Example scripts
1) Who am I + list Drive files
const me = await workspace.whoAmI();
const files = await workspace.call('drive', 'files.list', {
pageSize: 5,
fields: 'files(id,name,mimeType)'
});
state.lastEmail = me.email;
return {
user: me,
files: files.files,
remembered: state.lastEmail
};
2) List today’s calendar events
const start = new Date();
start.setHours(0, 0, 0, 0);
const end = new Date(start);
end.setDate(end.getDate() + 1);
return await workspace.call('calendar', 'events.list', {
calendarId: 'primary',
timeMin: start.toISOString(),
timeMax: end.toISOString(),
singleEvents: true,
orderBy: 'startTime'
});
OAuth and token storage
- First call without token triggers browser login automatically
- Default config directory:
~/.pi/google-workspace - Default token path:
~/.pi/google-workspace/token.json - Default auth mode:
cloud(unless overridden)
Environment variables
GOOGLE_WORKSPACE_CONFIG_DIRGOOGLE_WORKSPACE_CREDENTIALSGOOGLE_WORKSPACE_TOKENGOOGLE_WORKSPACE_AUTH_MODE(cloudorlocal)GOOGLE_WORKSPACE_CLIENT_IDGOOGLE_WORKSPACE_CLOUD_FUNCTION_URLGOOGLE_WORKSPACE_CALLBACK_HOST
Security notes
- Uses Node
vmfor execution convenience, not a hardened sandbox. - Treat this as trusted local tooling.
- Do not expose this server to untrusted users or networks.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。