
MCP fork of Google Workspace CLI
io.github.shigechikaPublished by GitHub account shigechikav0.22.5-mcp.38Updated Oct 24, 2026
MCP fork of Google Workspace CLI (Gmail, Drive, Calendar, and more)
Overview
MCP fork of the Google Workspace CLI, letting an assistant read and act across Drive, Gmail, Calendar, Sheets, Docs, Chat and other Workspace APIs.
- What you can do
- Work with Drive files: list, create, upload and download, with auto-pagination and NDJSON streaming.
- Handle Gmail: send, reply, reply-all, forward, triage unread mail, watch for new messages.
- Manage Calendar events and agendas, and read or append Google Sheets values and Docs text.
- Send Chat messages, run Apps Script pushes, and use workflow helpers such as standup reports, meeting prep and weekly digests.
- Introspect any Workspace API method's schema and call it directly, since the command surface is built from Google's Discovery Service at runtime.
- When to use it
- Useful when an assistant should work inside a real Google Workspace account: summarizing mail, drafting replies, scheduling or reviewing meetings, updating spreadsheets and documents, or uploading files. Suited to personal or team automation where you already have a Google Cloud project and are comfortable granting OAuth scopes.
- Requirements
- Runs as a local process, here as a Docker image over stdio. Needs a Google account with Workspace access and a Google Cloud project with OAuth credentials (a Desktop-app OAuth client, or a service account key). Credentials come from an interactive login, or from GOOGLE_WORKSPACE_CLI_TOKEN, GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE, or GOOGLE_WORKSPACE_CLI_CLIENT_ID with GOOGLE_WORKSPACE_CLI_CLIENT_SECRET. The optional setup command needs the gcloud CLI; network access to Google APIs is required.
Installation
In SourceWeft
- Open MCP fork of Google Workspace CLI in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
gws
One CLI for all of Google Workspace — built for humans and AI agents.
Drive, Gmail, Calendar, and every Workspace API. Zero boilerplate. Structured JSON output. 40+ agent skills included.
[!NOTE] This is not an officially supported Google product.
[npm version] [license] [CI status] [install size]
⬇️ Download the latest release for your OS
gws doesn't ship a static list of commands. It reads Google's own Discovery Service at runtime and builds its entire command surface dynamically. When Google Workspace adds an API endpoint or method, gws picks it up automatically.
[!IMPORTANT] This project is under active development. Expect breaking changes as we march toward v1.0.
Contents
- Prerequisites
- Installation
- Quick Start
- Why gws?
- Authentication
- AI Agent Skills
- Advanced Usage
- Environment Variables
- Exit Codes
- Architecture
- Troubleshooting
- Development
Prerequisites
- Node.js 18+ — for
npm install(or download a pre-built binary from GitHub Releases) - A Google Cloud project — required for OAuth credentials. You can create one via the Google Cloud Console or with the
gcloudCLI or with thegws auth setupcommand. - A Google account with access to Google Workspace
Installation
The recommended way to install gws is to download the pre-built binary for your OS and architecture from the GitHub Releases page. Extract the archive and place the gws binary in your $PATH.
For convenience, you can also use npm to automate downloading the appropriate binary from GitHub Releases:
Or build from source:
A Nix flake is also available at github:googleworkspace/cli
On macOS and Linux, you can also install via Homebrew:
Quick Start
Why gws?
For humans — stop writing curl calls against REST docs. gws gives you --help on every resource, --dry-run to preview requests, and auto‑pagination.
For AI agents — every response is structured JSON. Pair it with the included agent skills and your LLM can manage Workspace without custom tooling.
Authentication
The CLI supports multiple auth workflows so it works on your laptop, in CI, and on a server.
Which setup should I use?
Interactive (local desktop)
Credentials are encrypted at rest (AES-256-GCM) with the key stored in your OS keyring (or ~/.config/gws/.encryption_key when GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=file).
gws auth setuprequires thegcloudCLI. If you don't havegcloud, use the manual setup below instead.
[!WARNING] Scope limits in testing mode: If your OAuth app is unverified (testing mode), Google limits consent to ~25 scopes. The
recommendedscope preset includes 85+ scopes and will fail for unverified apps (especially for@gmail.comaccounts). Choose individual services instead to filter the scope picker:
Manual OAuth setup (Google Cloud Console)
Use this when gws auth setup cannot automate project/client creation, or when you want explicit control.
- Open Google Cloud Console in the target project:
- OAuth consent screen:
https://console.cloud.google.com/apis/credentials/consent?project=<PROJECT_ID> - Credentials:
https://console.cloud.google.com/apis/credentials?project=<PROJECT_ID>
- OAuth consent screen:
- Configure OAuth branding/audience if prompted:
- App type: External (testing mode is fine)
- Add your account under Test users
- Create an OAuth client:
- Type: Desktop app
- Download the client JSON and save it to:
~/.config/gws/client_secret.json
[!IMPORTANT] You must add yourself as a test user. In the OAuth consent screen, click Test users → Add users and enter your Google account email. Without this, login will fail with a generic "Access blocked" error.
Then run:
Browser-assisted auth (human or agent)
You can complete OAuth either manually or with browser automation.
- Human flow: run
gws auth login, open the printed URL, approve scopes. - Agent-assisted flow: the agent opens the URL, selects account, handles consent prompts, and returns control once the localhost callback succeeds.
If consent shows "Google hasn't verified this app" (testing mode), click Continue. If scope checkboxes appear, select required scopes (or Select all) before continuing.
Headless / CI (export flow)
- Complete interactive auth on a machine with a browser.
- Export credentials:
- On the headless machine:
Service Account (server-to-server)
Point to your key file; no login needed.
Pre-obtained Access Token
Useful when another tool (e.g. gcloud) already mints tokens for your environment.
Precedence
Environment variables can also live in a .env file.
AI Agent Skills
The repo ships 100+ Agent Skills (SKILL.md files) — one for every supported API, plus higher-level helpers for common workflows and 50 curated recipes for Gmail, Drive, Docs, Calendar, and Sheets. See the full Skills Index for the complete list.
OpenClaw setup
The gws-shared skill includes an install block so OpenClaw auto-installs the CLI via npm if gws isn't on PATH.
Gemini CLI Extension
-
Authenticate the CLI first:
-
Install the extension into the Gemini CLI:
Installing this extension gives your Gemini CLI agent direct access to all gws commands and Google Workspace agent skills. Because gws handles its own authentication securely, you simply need to authenticate your terminal once prior to using the agent, and the extension will automatically inherit your credentials.
Advanced Usage
Multipart Uploads
Pagination
Google Sheets — Shell Escaping
Sheets ranges use ! which bash interprets as history expansion. Always wrap values in single quotes:
Helper Commands
Some services ship hand-crafted helper commands alongside the auto-generated Discovery surface. Helper commands are prefixed with + so they are visually distinct and never collide with Discovery-generated method names.
Time-aware helpers (+agenda, +standup-report, +weekly-digest, +meeting-prep) automatically use your Google account timezone (fetched from Calendar Settings API and cached for 24 hours). Override with --timezone/--tz on +agenda, or set the --timezone flag for explicit control.
Run gws <service> --help to see both Discovery methods and helper commands together.
Full helper reference:
Examples:
Model Armor (Response Sanitization)
Integrate Google Cloud Model Armor to scan API responses for prompt injection before they reach your agent.
Environment Variables
All variables are optional. See .env.example for a copy-paste template.
Environment variables can also be set in a .env file (loaded via dotenvy).
Exit Codes
gws uses structured exit codes so scripts can branch on the failure type without parsing error output.
Architecture
gws uses a two-phase parsing strategy:
- Read
argv[1]to identify the service (e.g.drive) - Fetch the service's Discovery Document (cached 24 h)
- Build a
clap::Commandtree from the document's resources and methods - Re-parse the remaining arguments
- Authenticate, build the HTTP request, execute
All output — success, errors, download metadata — is structured JSON.
Troubleshooting
"Access blocked" or 403 during login
Your OAuth app is in testing mode and your account is not listed as a test user.
Fix: Open the OAuth consent screen in your GCP project → Test users → Add users → enter your Google account email. Then retry gws auth login.
"Google hasn't verified this app"
Expected when your app is in testing mode. Click Advanced → Go to <app name> (unsafe) to proceed. This is safe for personal use; verification is only required to publish the app to other users.
Too many scopes / consent screen error
Unverified (testing mode) apps are limited to ~25 OAuth scopes. The recommended scope preset includes many scopes and will exceed this limit.
Fix: Select only the scopes you need:
gcloud CLI not found
gws auth setup requires the gcloud CLI to automate project creation. You have three options:
- Install gcloud and use
gclouddirectly. - Re-run
gws auth setupwhich wrapsgcloudcalls. - Skip
gcloudentirely — set up OAuth credentials manually in the Cloud Console
redirect_uri_mismatch
The OAuth client was not created as a Desktop app type. In the Credentials page, delete the existing client, create a new one with type Desktop app, and download the new JSON.
API not enabled — accessNotConfigured
If a required Google API is not enabled for your GCP project, you will see a
403 error with reason accessNotConfigured:
gws also prints an actionable hint to stderr:
Steps to fix:
- Click the
enable_urllink (or copy it from theenable_urlJSON field). - In the GCP Console, click Enable.
- Wait ~10 seconds, then retry your
gwscommand.
[!TIP] You can also run
gws auth setupwhich walks you through enabling all required APIs for your project automatically.
Development
License
Apache-2.0
Disclaimer
[!CAUTION] This is not an officially supported Google product.
Source: README.md at commit d12261b
Tools
0Version history
2- v0.22.5-mcp.38LatestOct 1, 2026
- v0.22.5-mcp.36Sep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts