google_workspace_mcp

Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool

Runssource: GitHubhomepagePythonMITcommit ed70fb906823

Python, MIT licensed. The project labels itself: ai, chatgpt, claude, claude code, claude desktop, gmail, google calendar and google chat.

google_workspace_mcp runs. An Argusic agent installed it in 0.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

workspace-mcp 1.29.0 installed from source; all 2686 tests pass; CLI 'workspace-mcp --help' and 'workspace-cli --help' both print usage; server starts on stdio transport with 'core' tool tier.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 86 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
86 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
3,526
forks
1,127
open issues
91
watchers
20
size
20 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Install time
under a minute
Cold machine to finish
5 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
2686 passed, 2 skipped, 1 warning in 49.17s via 'pytest --ignore=tests/gappsscript/manual_test.py --tb=short -q'
Model tokens used
123,823
Exact commit tested
ed70fb906823
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- Test runs: ~50s each, ran 3 times (first run ~48s + second ~49s + incremental ~5s)
Total: roughly 10 minutes.
Here's my final report:
tokens used
123,823
Everything passed. Let me now record the final result.
It took about 3 min to install uv, 5 min to install deps, 1 min to run tests, total ~9 min. Let me …
- uv install: ~5s
- uv sync: ~5s
- Test runs: ~50s each, ran 3 times (first run ~48s + second ~49s + incremental ~5s)
Total: roughly 10 minutes.
Here's my final report:

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 0.5 minutes, faster than the median of the 234 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 235 ai projects Argusic has installed and timed, google_workspace_mcp was the 14th fastest to reach a running state, and 166 of 235 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 0.5 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.03
Argusic Runner1/3Runs with mocks72.000.12

Topics (from GitHub)

aichatgptclaudeclaude-codeclaude-desktopgmailgoogle-calendargoogle-chatgoogle-docsgoogle-drivegoogle-formsgoogle-sheetsgoogle-tasksgoogle-workspacegsuitellmllm-toolsmcpmcp-servermodel-context-protocol-server

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/google_workspace_mcp.svg)](https://argusic.com/subject/google-workspace-mcp)

Questions

Does google_workspace_mcp run?
Yes. google_workspace_mcp runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test google_workspace_mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ed70fb906823. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test google_workspace_mcp?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does google_workspace_mcp take to install?
0.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does google_workspace_mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing google_workspace_mcp?
Nothing did, in the recorded run: zero errors between clone and running.
How does google_workspace_mcp compare with the alternatives?
Of the 235 ai projects Argusic has installed and timed, google_workspace_mcp was the 14th fastest to reach a running state, and 166 of 235 reached one at all.
Where is the evidence for google_workspace_mcp?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion