gws-mcp
A small MCP server for read-write access to Google Tasks, Calendar, and Drive, enforcing human approval for all mutating operations.
README
gws-mcp
A small, self-contained MCP server for Google Tasks, Calendar, and Drive — read-write, with one hard rule: every write requires explicit human approval before it executes.
Status: alpha (v0.1.0). The full designed surface — 25 tools across Tasks, Calendar, and Drive — is implemented and tested (46 tests, both approval modes). Not yet battle-hardened against real-world API quirks.
Why another Google MCP?
There is no official Google MCP server for consumer Workspace data, and the community options are broad (10+ services) and mostly unmaintained. This one is deliberately narrow:
- Three services only — Tasks, Calendar, Drive. Smaller code, smaller audit surface.
- Local stdio server — spawned by your MCP client (Claude Code, Gemini CLI, …). Nothing hosted, nothing listening on a network. The server only ever sees tool calls, never your prompts.
- BYO OAuth — you create your own Google Cloud OAuth client and grant scopes to yourself. No shared credentials anywhere.
- Tokens in the OS keyring (Secret Service / KDE Wallet / macOS Keychain) — never plaintext on disk.
The write-approval invariant
Read tools (list_*, get_*, search_*, read_*) run freely. Mutating
tools (create_*, update_*, complete_*, move_*, trash_*, delete_*)
cannot execute without a human saying yes, enforced in layers:
- MCP elicitation (primary): before executing, the server sends a human-readable preview through the client UI — the confirmation goes directly to the human, so the model cannot approve its own writes.
- Two-step fallback (clients without elicitation): the first call returns a preview + one-time confirm token and mutates nothing; only a second call with the token executes. All executed writes are logged to stderr.
- Tool annotations (
readOnlyHint/destructiveHint) + the strict naming convention, so client permission systems can auto-allow reads and always-prompt writes.
Destructive operations are softened where the API allows it: Drive "delete" is trash, never a hard delete.
Planned tool surface (~22 tools)
| Service | Read | Write (approval-gated) |
|---|---|---|
| Tasks | list_task_lists list_tasks get_task |
create_task update_task complete_task move_task delete_task |
| Calendar | list_calendars list_events search_events get_event |
create_event update_event respond_to_event delete_event |
| Drive | search_files get_file_metadata read_file_content |
create_file update_file_content move_file trash_file |
OAuth scopes: tasks, calendar.events (events only — no ACL/settings
access), drive.
Stack
Python 3.12+ · uv · official
mcp SDK (FastMCP,
stdio) · google-api-python-client + google-auth-oauthlib · keyring ·
pytest + ruff.
Quick start
- Bring your own OAuth client (one-time, ~30 min): in the Google Cloud
console create a project, enable the Tasks, Calendar, and Drive
APIs, create an OAuth 2.0 Desktop app client, and download its JSON to
~/.config/gws-mcp/credentials.json(chmod 600). No credentials ever ship with, or are stored by, this project — the OAuth grant lives in your OS keyring. - Authenticate (interactive, opens a browser):
git clone https://github.com/purplespacecat/gws-mcp && cd gws-mcp uv sync uv run gws-mcp auth # then: uv run gws-mcp auth --status - Wire it into your MCP client (stdio):
In clients that support MCP elicitation, write approvals appear as UI prompts; in clients that don't, writes return a preview + one-time confirm token and nothing mutates until# Claude Code claude mcp add google-workspace -- uv --directory /path/to/gws-mcp run gws-mcp # Gemini CLI gemini mcp add google-workspace uv -- --directory /path/to/gws-mcp run gws-mcpconfirm_writeis called.
Contributing
Issues and PRs are welcome — see CONTRIBUTING.md. All contributions are reviewed before merge; PRs that touch auth, scopes, or the write-approval layer get extra scrutiny.
License
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。