gws-mcp
The gws-mcp server provides read and write access to Google Tasks, Calendar, and Drive, running locally via stdio using your own Google Cloud OAuth credentials. All write operations require explicit human approval.
Authentication: Check the current Google auth status (
auth_status).Google Tasks: List task lists, list/get tasks. Create, update, complete, move, and delete tasks (writes approval-gated).
Google Calendar: List calendars, list/search/get events. Create, update, respond to, and delete events (writes approval-gated).
Google Drive: Search files, get metadata, read file content. Create files, update content, move files, and trash files — hard delete is not supported (writes approval-gated).
Write Approval: Enforced via MCP elicitation (primary) or a two-step preview/confirm token fallback. Destructive actions are explicitly gated and logged.
Privacy: Runs locally, not network-hosted; OAuth tokens are stored securely in the OS keyring.
Provides read and write operations for Google Tasks, including listing task lists and tasks, creating, updating, completing, moving, and deleting tasks, with every write requiring explicit human approval.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@gws-mcpAdd a task 'Review PR' to my work list"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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?
Google now ships official remote MCP servers (Developer Preview) for Gmail, Drive, Calendar, Chat and People — hosted HTTP endpoints you wire into a client as connectors. They do not cover Google Tasks, they execute writes as soon as the model calls the tool (no built-in approval step), and they are remote by design. Community alternatives remain broad (10+ services) and mostly unmaintained.
This server is deliberately narrow and local — it pairs well with the official connectors, filling the Tasks gap and covering Calendar/Drive when you want approval-gated writes or a fully local path:
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.
Related MCP server: Google Docs + Gmail MCP Server
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 |
|
|
Calendar |
|
|
Drive |
|
|
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 --statusWire it into your MCP client (stdio):
# 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-mcpIn 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
confirm_writeis called.
Serving a subset of services
Set GWS_MCP_SERVICES (comma-separated: tasks, calendar, drive) to
expose only some services — e.g. only Tasks, if you use Google's official
remote MCP servers for Calendar and Drive:
claude mcp add google-tasks --env GWS_MCP_SERVICES=tasks -- \
uv --directory /path/to/gws-mcp run gws-mcpThis narrows both the tools the server exposes and the scopes
gws-mcp auth requests — a Tasks-only install never asks for the restricted
drive scope. Run the auth flow with the same value set
(GWS_MCP_SERVICES=tasks uv run gws-mcp auth); widening services later means
re-running it to consent to the added scopes.
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
Available Tools
1 toolauth_statusARead-only
Report Google authentication status (never contains secret material).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, but the description adds the important behavioral note 'never contains secret material', which is beyond what annotations provide. This enriches transparency about the tool's safety and content. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of a single, well-structured sentence that front-loads the action ('Report Google authentication status') and adds a critical safety qualifier. Every word serves a purpose; zero waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and a simple purpose, the description is nearly complete. It could be improved by mentioning the expected output format (e.g., a status string or object), but the current content still provides sufficient context for an AI agent to understand the tool's function.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters, so schema coverage is 100% trivially. The description does not need to add parameter information. With zero parameters, the baseline score is 4, and the description adds sufficient context about the tool's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'report' and clearly identifies the resource as 'Google authentication status'. It provides precise scope with the clarification 'never contains secret material'. With no sibling tools, differentiation is not required, making this fully clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives. However, the tool has no siblings and is simple, so the lack of explicit usage context is acceptable but not ideal. A score of 3 reflects minimal viability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
auth_status
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of ambiguity or confusion between tools.
With a single tool, naming is trivially consistent and follows a clear pattern (verb_noun: auth_status).
A single tool for checking authentication status is extremely limited for a server named 'gws-mcp' which implies Google Workspace functionality. While it may serve a narrow purpose, the count feels too small for a meaningful integration.
The server only offers an auth status check, which is severely incomplete for any realistic Google Workspace interaction. There are no tools for managing resources, performing actions, or accessing data, so agents would hit dead ends immediately.
Maintenance
Related MCP Connectors
Streamable HTTP MCP server for Google Calendar and Sheets with OAuth login.
Hosted Google Calendar MCP server for AI agents. No self-hosting or Google Cloud setup.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that seamlessly interacts with your Google Calendar, Gmail, Drive and so on.30MIT
- AlicenseNot gradedqualityDmaintenanceA lightweight MCP server that integrates with Google Docs and Gmail, allowing AI workflows to append to Google Docs and create Gmail drafts with human approval.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceA lightweight MCP server for managing Google Workspace services (Gmail, Calendar, Drive, Docs, Sheets, Slides) through natural language with AI assistants like Claude and Cursor.9 npm1MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for Google Calendar and Google Tasks, exposed over HTTP (JSON-RPC) so LLM clients can manage events and tasks via a service account.85 npmMIT