Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add GoogleCloudPlatform/gemini-cloud-assist-mcp/plugin install cloud-operatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/googlecloudplatform/gemini-cloud-assist-mcp/setup)<a href="https://agentmods.dev/commands/googlecloudplatform/gemini-cloud-assist-mcp/setup"><img src="https://agentmods.dev/badge/commands/googlecloudplatform/gemini-cloud-assist-mcp/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/googlecloudplatform/gemini-cloud-assist-mcp/setup"><img src="https://agentmods.dev/badge/commands/googlecloudplatform/gemini-cloud-assist-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.03107 |
| Opus 5.5 | $0.00012 | $0.01243 |
| Sonnet 5.5 | $0.00006 | $0.00621 |
| Haiku 4.5 | $0.00003 | $0.00311 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk the user through Cloud Operator setup one step at a time. Wait for the user to confirm each console step before moving on. Run shell commands yourself where noted; never ask the user to do something you can do.
Constants:
- MCP server name:
autocloud - Endpoint:
https://geminicloudassist.googleapis.com/mcp/autocloud - OAuth client type, if the user creates a new client: Desktop app (Claude Code uses a random localhost callback port; Desktop clients accept any loopback port, Web clients don't)
- Tool timeout:
1800000ms (30 minutes) - Registration script:
${CLAUDE_PLUGIN_ROOT}/scripts/register-mcp.sh
Step 0 — Check current state and read the onboarding guide
The plugin ships an onboarding guide, ${CLAUDE_PLUGIN_ROOT}/onboarding.md. It holds the details and the troubleshooting table. Read it now, and read its Troubleshooting section whenever a step below fails.
Run claude mcp get autocloud. If its URL isn't the Endpoint above, register the server again in Step 4 with the user's existing OAuth client, even if it reports "Connected", then skip the steps that are already done. Otherwise, if it reports "Connected", tell the user the autocloud MCP server is already set up and skip to Step 4b, which checks their operator project and agent, then Step 5 (offer to update preferences). If an autocloud server exists in local or project scope, note it — it would shadow the user-scope server this setup creates — and offer to remove it at the end.
Step 1 — Choose the OAuth client project
First, ask whether the user already has an OAuth client ID and secret. If they do, skip to Step 4 with that client, after checking two things.
- Ask whether it's a Desktop app or a Web application client. For a Web application client, ask for the port in its redirect URI,
http://localhost:<PORT>/callback, because Step 4 needs it. It's under Authorized redirect URIs in the client's settings. - An existing client only signs in the accounts its owner allows. The owner must add the user's account as a test user of an External client, or the account must belong to the organization of an Internal one.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 117 lines · 29 tokens per session scan A 1a794048af0d
setup is a command published in the GitHub repository GoogleCloudPlatform/gemini-cloud-assist-mcp (69 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,107 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other commands, from other repositories
deploy-schema
Deploy Sanity schema to the Content Lake with verification.
wasm-split
Command "wasm-split" from getsentry/toolkit, covering examples, add a build id to a module, in place, and print it, capture the build id for a later upload, also drop function names from the shipped binary and point browsers at a companion served from a cdn.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.