MCP server
by googlecloudplatform
Connect Gemini Cloud Assist to Google Cloud APIs for speech to text, speech recognition, and Drive management via natura
Connects to Google Cloud's Gemini Cloud Assist APIs to create, run, and manage troubleshooting investigations for your Google Cloud environment using natural language.
Gemini Cloud Assist is an official MCP server published by googlecloudplatform that provides AI assistants with tools and capabilities via the Model Context Protocol. Connect Gemini Cloud Assist to Google Cloud APIs for speech to text, speech recognition, and Drive management via natura It is categorized under cloud infrastructure. This server exposes 4 tools that AI clients can invoke during conversations and coding sessions.
You can install Gemini Cloud Assist in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
Apache-2.0
Gemini Cloud Assist is released under the Apache-2.0 license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
According to our notes, Gemini Cloud Assist benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Gemini Cloud Assist is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
According to our notes, Gemini Cloud Assist benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
I recommend Gemini Cloud Assist for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Gemini Cloud Assist reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We evaluated Gemini Cloud Assist against two servers with overlapping tools; this profile had the clearer scope statement.
We wired Gemini Cloud Assist into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Strong directory entry: Gemini Cloud Assist surfaces stars and publisher context so we could sanity-check maintenance before adopting.
We wired Gemini Cloud Assist into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
I recommend Gemini Cloud Assist for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
showing 1-10 of 38
This server connects Model Context Protocol (MCP) clients such as the Gemini CLI to the Gemini Cloud Assist APIs. It allows you to use natural language to understand, manage, and troubleshoot your Google Cloud environment directly from the local command line.
[!NOTE] The Google Cloud Platform Terms of Service (available at https://cloud.google.com/terms/) and the Data Processing and Security Terms (available at https://cloud.google.com/terms/data-processing-terms) do not apply to any component of the Gemini Cloud Assist MCP Server software.
To learn more about Gemini Cloud Assist, see the Gemini Cloud Assist overview in the Google Cloud documentation.
Before you begin, ensure you have the following set up:
roles/serviceusage.serviceUsageAdmin: Required to enable the Cloud Assist APIs.roles/geminicloudassist.user: Required to make requests to the Cloud Assist APIs.The Gemini Cloud Assist MCP server uses local Application Default Credentials (ADC) to securely authenticate to Google Cloud. To set up ADC, run the following gcloud commands:
# Authenticate your user account to the gcloud CLI
gcloud auth login
# Set up Application Default Credentials for the server.
# This allows the MCP server to securely make Google Cloud API calls on your behalf.
gcloud auth application-default login
Below is the standard configuration snippet you will use. It tells the client to use npx to download and run the latest version of the MCP server on demand. Paste the MCP configuration to an MCP client of your choosing. We recommend using the Gemini CLI for the best experience.
"mcpServers" : {
"GeminiCloudAssist": {
"command": "npx",
"args": ["-y", "@google-cloud/gemini-cloud-assist-mcp@latest"],
"timeout": 600000
}
}
Install the MCP server as a Gemini CLI extension:
gemini extensions install https://github.com/GoogleCloudPlatform/gemini-cloud-assist-mcp
Validate successful installation by running:
gemini extensions list
Add the MCP config to the ~/.gemini/settings.json. This gives you access to MCP Tools in every Gemini CLI session.
Add the MCP config to your /path/to/project/.gemini/settings.json file. This gives you access to the MCP Tools in Gemini CLI sessions created under this project folder only.
claude mcp add GeminiCloudAssist npx -y @google-cloud/gemini-cloud-assist-mcp@latest
Follow detailed instructions on Anthropic's documentation for more information.
Update cline_mcp_settings.json with the MCP config.
Follow detailed instructions on Cline's website for more information.
create_investigation: Creates a new Gemini Cloud Assist investigation.run_investigation: Runs an existing Gemini Cloud Assist investigation that you created.add_observation: Adds a new observation to an existing investigation to refine its analysis.fetch_investigation: Get investigation details or list investigations in your project.This section shows examples of the tasks you can perform with the Cloud Assist MCP server with the Gemini CLI, including example prompts and responses.
<details> <summary>Create and run investigations</summary>Using 1 MCP server (Ctrl+T to view descriptions)
╭───────────────────────────────────────────────────────────────────────────────────╮
│ > Investigate the pending pods issue in my test-cluster-1 cluster │
╰───────────────────────────────────────────────────────────────────────────────────╯
✦ I can help with that. I'll start an investigation into the pending pods issue in
your test-cluster-1 cluster. To do that, I'll run a few commands to get the
information I need to start the investigation.
╭──────────────────────────────────────────────────────────────────────────────────╮
│ ✔ Shell gcloud config get-value project (Getting the configured GCP project.) |
... |
... |
╰──────────────────────────────────────────────────────────────────────────────────╯
✦ I'll now create an investigation into the pending pods issue in your test-cluster-1 GKE cluster.
╭──────────────────────────────────────────────────────────────────────────────────╮
│ ✔ create_investigation (gemini-cloud-assist-mcp MCP Server) create_investigati… │
│ │
│ ## Gemini Cloud Assist Investigation │
│ │
│ **Name**: [Gemini CLI] Pending pods in test-cluster-1 GKE cluster │
... |
... |
╰──────────────────────────────────────────────────────────────────────────────────╯
✦ I've created the investigation. Now I'll run it to analyze the issue.
╭──────────────────────────────────────────────────────────────────────────────────╮
│ ✔ run_investigation (gemini-cloud-assist-mcp MCP Server) run_investigation (ge… │
... |
... |
╰──────────────────────────────────────────────────────────────────────────────────╯
✦ The investigation is complete. Here's what I found:
The main problem is that your GKE cluster `test-cluster-1` is out of resources. It
has only one node, and that node is full. This is causing new pods to get stuck in
a "pending" state because there's no room for them.
The investigation also revealed that Node Auto-Provisioning (NAP) is disabled. This
is a key feature that allows the cluster to automatically add more nodes when it's
running low on resources. Because NAP is disabled, the cluster can't scale up to
meet the demand.
I have two recommendations to fix this:
1. Enable Node Auto-Provisioning for the test-cluster-1 cluster. This is the best
long-term solution because it will allow the cluster to automatically scale up
and down as needed.
2. Manually add more nodes to the cluster. This is a good short-term solution that
will immediately relieve the resource pressure and allow the pending pods to
be scheduled.
I recommend that you start by enabling Node Auto-Provisioning. I can do this for
you now, or you can do it yourself by following the instructions in the official
documentation (https://cloud.google.com/kubernetes-engine/docs/how-to/node-auto-pro
visioning#enable).
What would you like to do?
✦ The investigation is complete. Here's a summary of the findings:
Primary Cause:
* Ephemeral Storage Exhaustion: The main reason for the pod crashes is
that the GKE nodes are running out of ephemeral storage. This is
causing a DiskPressure condition on the nodes, which in turn leads to
the kubelet evicting pods to free up space.
╭───────────────────────────────────────────────────────────────────────────────────╮
│ > Do you know which pod is consuming all the storage space? │
╰───────────────────────────────────────────────────────────────────────────────────╯
✦ That's a great question. The investigation points to the emptyDir volume
in the gke-00
---
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.