Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View All AI Agent Use Cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

Google Cloud Compute MCP Server
for AI Agents

Production-ready Google Cloud Compute MCP server with 40 extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →
Google Cloud Compute logo
Google Cloud Compute MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

40 Agent Actions

Create, read, update, and delete across Google Cloud Compute — and extend your agent's capabilities with custom actions.

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Google Cloud Compute MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Google Cloud Compute tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Google Cloud Compute call.

Tools Discovery →

What is the Google Cloud Compute MCP Server?

A Google Cloud Compute MCP server lets AI agents read and write Google Cloud Compute data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google Cloud Compute MCP server ships with 40 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Google Cloud Compute MCP Tools and Actions

Every action from Google Cloud Compute's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Artifact Packages

  • List Artifact Packages

    List packages in an Artifact Registry repository

  • Get Artifact Package

    Get details of a specific package in Artifact Registry

Artifact Docker Images

  • List Artifact Docker Images

    List Docker images in an Artifact Registry repository

  • Get Artifact Docker Image

    Get details of a specific Docker image in Artifact Registry

Cloud Functions

  • List Cloud Functions

    List Cloud Functions in a specific location

  • Get Cloud Function

    Get details of a specific Cloud Function

  • Delete Cloud Function

    Delete a Cloud Function

Cloud Run Services

  • List Cloud Run Services

    List Cloud Run services in a specific location

  • Get Cloud Run Service

    Get details of a specific Cloud Run service

  • Delete Cloud Run Service

    Delete a Cloud Run service

Cloud Run Revisions

  • List Cloud Run Revisions

    List revisions of a Cloud Run service

  • Get Cloud Run Revision

    Get details of a specific Cloud Run revision

Disks

  • List Disks

    List persistent disks in a specific zone

  • Get Disk

    Get details of a specific persistent disk

Images

  • List Images

    List images in a GCP project

  • Get Image

    Get details of a specific image

Instance Groups

  • List Instance Groups

    List instance groups in a specific zone

  • Get Instance Group

    Get details of a specific instance group

Managed Instance Groups

  • List Managed Instance Groups

    List managed instance group managers in a specific zone

  • Get Managed Instance Group

    Get details of a specific managed instance group manager

Instances

  • List Instances

    List VM instances in a specific zone

  • Get Instance

    Get details of a specific VM instance

  • Delete Instance

    Delete a VM instance

Compute Zones

  • List Compute Zones

    List all available zones in a GCP project

  • Get Compute Zone

    Get details of a specific zone in a GCP project

Compute Regions

  • List Compute Regions

    List all available regions in a GCP project

  • Get Compute Region

    Get details of a specific region in a GCP project

Other (13)

  • Create Disk Snapshot

    Create a snapshot of a persistent disk

  • List Artifact Repositories

    List Artifact Registry repositories in a specific location

  • Get Artifact Repository

    Get details of a specific Artifact Registry repository

  • List Artifact Versions

    List versions of a package in Artifact Registry

  • List Instance Group Instances

    List instances in a specific instance group

  • List Instances (Aggregated)

    List VM instances across all zones in a project

  • Resize Managed Instance Group

    Resize a managed instance group to the specified size

  • Start Instance

    Start a stopped VM instance

  • Stop Instance

    Stop a running VM instance

  • Reset Instance

    Reset a VM instance (hard reset)

  • Suspend Instance

    Suspend a running VM instance

  • Resume Instance

    Resume a suspended VM instance

  • Test Auth

    Verify Google Cloud Compute credentials

Set Up Your Google Cloud Compute MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Google Cloud Compute in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Google Cloud Compute MCP Server Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

Google Cloud Compute MCP Server FAQ

Google Cloud Compute MCP server vs direct API integration — what's the difference?
A Google Cloud Compute MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Google Cloud Compute. A Google Cloud Compute MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Google Cloud Compute at runtime. StackOne provides both.
How does Google Cloud Compute authentication work for AI agents?
Google Cloud Compute authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Google Cloud Compute account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Google Cloud Compute MCP tools vulnerable to prompt injection?
Yes — Google Cloud Compute MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Google Cloud Compute agent and how do I avoid it?
Context bloat happens when Google Cloud Compute tool schemas and API responses eat your Google Cloud Compute agent's memory, preventing it from reasoning effectively. A single Google Cloud Compute query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Google Cloud Compute agent can access?
Yes — you can limit which actions your Google Cloud Compute agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Google Cloud Compute MCP server?
Yes — you can create custom agent actions for your Google Cloud Compute MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Google Cloud Compute's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Google Cloud Compute MCP server?
Skip a Google Cloud Compute MCP server if your integration is purely software-to-software — direct Google Cloud Compute API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Google Cloud Compute actions at runtime.
What AI frameworks and AI clients does the StackOne Google Cloud Compute MCP server support?
The StackOne Google Cloud Compute MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo