mcpField
G
gcp-vertexai

gcp-vertexai

github.com/alphaonedevCloud & DevOps48 installs
Repository

About gcp-vertexai

gcp-vertexai is a skill for planning Google Cloud provisioning and operations, aimed at teams working with GCP and Vertex AI. It provides architecture guidance, cost modeling, and pre-flight requirements, while Google Cloud Python libraries perform operations.

Key features

  1. 01GCP service selection guidance
  2. 02Cost estimation and optimization
  3. 03IAM and identity federation prerequisites
  4. 04Infrastructure-as-code approach guidance
  5. 05Vertex AI agent architecture guidance

Use cases

  1. 01Compare GCP service options
  2. 02Estimate and optimize cloud costs
  3. 03Plan IAM prerequisites before provisioning
  4. 04Design multi-agent workflows with Vertex AI Agent Engine

MCP support

The skill identifies Vertex AI Extensions as MCP-compatible. It does not itself describe an MCP server or client.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/alphaonedev/openclaw-graph --skill gcp-vertexai

After installing, type/gcp-vertexaiin Claude Code to confirm it loaded.

Details

From the project README

gcp-vertexai

Google Cloud Integration

This skill delegates all GCP provisioning and operations to the official Google Cloud Python client libraries.

# Core GCP client library
pip install google-cloud-python

# Vertex AI + Agent Engine (AI/ML workloads)
pip install google-cloud-aiplatform

# Specific service clients (install only what you need)
pip install google-cloud-bigquery      # BigQuery
pip install google-cloud-storage       # Cloud Storage
pip install google-cloud-pubsub        # Pub/Sub
pip install google-cloud-run           # Cloud Run

SDK Docs: https://github.com/googleapis/google-cloud-python Vertex AI SDK: https://cloud.google.com/vertex-ai/docs/python-sdk/use-vertex-ai-python-sdk

Use the Google Cloud Python SDK for all GCP provisioning and operational actions. This skill provides architecture guidance, cost modeling, and pre-flight requirements — the SDK handles execution.

Architecture Guidance

Consult this skill for:

  • GCP service selection and trade-off analysis
  • Cost estimation and optimization (committed use discounts, sustained use)
  • Pre-flight IAM / Workload Identity Federation requirements
  • IaC approach (Terraform AzureRM vs Deployment Manager vs Config Connector)
  • Integration patterns with Google Workspace and other GCP services
  • Vertex AI Agent Engine for multi-agent workflow design

Agent & AI Capabilities

CapabilityTool
LLM agentsVertex AI Agent Engine
Model servingVertex AI Model Garden
RAGVertex AI Search + Embeddings API
Multi-agentAgent Development Kit (google/adk-python)
MCPVertex AI Extensions (MCP-compatible)

Reference

Comments

Markdown supported