菜单
Configure, install, and maintain Google-managed and self-hosted MCP servers for GCP. Covers setup, auth (ADC and SA key), capability map, troubleshooting, and version tracking. Every MCP entry includes a gcloud CLI fallback.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
100% Google Cloud focused architect. Receives the GCP-scoped portion of the solution-designer HLD. Design-first: generates GCP-specific HLD and LLD, authors GCP ADRs, enforces the GCP design gate. Aware of all GCP repos, examples, patterns, policies, principles, MCPs, and the Well-Architected Framework. Does not make vendor-selection decisions — those belong to solution-designer.
Configure observability on GCP using Cloud Logging, Cloud Monitoring, Cloud Trace, and Cloud Profiler. Covers log sinks, log-based metrics, alerting policies, dashboards, and uptime checks. Owns the operational readiness evidence for gcp-ops.
Deploy and manage containerized workloads on Cloud Run. Covers service creation, traffic splitting, IAM, VPC connectivity, secrets integration, auto-scaling, and gcloud CLI patterns. Warns before billable deployments.
Deploy and manage Kubernetes workloads on Google Kubernetes Engine (GKE). Covers Autopilot and Standard modes, Workload Identity, node pool management, networking, security, and gcloud/kubectl CLI patterns. Warns before cluster creation (billable).
Design and manage GCP networking: VPC, subnets, firewall rules, Cloud Load Balancing, Cloud Armor, Private Google Access, and Shared VPC. Deny-by-default firewall posture. Warns before creating external load balancers (billable).
Agentic systems architect for the Gemini Enterprise Agent Platform (GEAP, formerly Vertex AI). Tier 2 specialist alongside gcp-architect: owns agentic application design AND agent evaluation execution. Covers ADK, Agent Runtime (formerly Agent Engine), the MCP/A2A/AP2 protocol stack, multi-agent topologies, grounding/RAG, memory, human-in-the-loop, and Gemini model selection. GCP is always the target deployment platform.
| name | mcp-servers |
| description | Configure, install, and maintain Google-managed and self-hosted MCP servers for GCP. Covers setup, auth (ADC and SA key), capability map, troubleshooting, and version tracking. Every MCP entry includes a gcloud CLI fallback. |
| version | 0.1 |
| triggers | ["MCP server","MCP setup","google MCP","model context protocol GCP","MCP install","MCP auth","genai toolbox","MCP tools GCP","configure MCP"] |
| required_scopes | [] |
| mcp_servers | ["google-cloud-run","google-bigquery","google-gke","google-storage","google-vertex-ai","google-iam","google-logging","google-monitoring"] |
Configure and maintain Model Context Protocol (MCP) servers for Google Cloud. All auth flows through ADC or explicit SA key path — no credential values stored anywhere.
All GCP MCP servers authenticate via Application Default Credentials (ADC):
# Authenticate locally (developer machine)
gcloud auth application-default login
# Authenticate for a service account (CI/CD or production agent)
gcloud auth activate-service-account --key-file=/path/to/sa-key.json
gcloud auth application-default login --impersonate-service-account=SA@PROJECT.iam.gserviceaccount.com
| Server | Capability | Required Role |
|---|---|---|
google-cloud-run | Deploy/manage Cloud Run services | roles/run.admin |
google-bigquery | Query/manage BigQuery datasets | roles/bigquery.user |
google-gke | GKE cluster management | roles/container.developer |
google-storage | Cloud Storage bucket ops | roles/storage.objectAdmin |
google-vertex-ai | Vertex AI model/endpoint management | roles/aiplatform.user |
google-iam | IAM policy management | roles/iam.securityAdmin |
google-logging | Cloud Logging query/ingest | roles/logging.viewer |
google-monitoring | Metrics, alerting | roles/monitoring.viewer |
Google's MCP Toolbox for Databases enables LLM agents to query Cloud SQL, AlloyDB, Spanner, BigQuery, and more safely.
# Run the toolbox MCP server (requires a tools.yaml pointing at your database)
# Tested 2026-07-23: this is the correct package. Full docs: https://mcp-toolbox.dev
npx -y @toolbox-sdk/server --stdio --config tools.yaml
# Example tools.yaml (BigQuery source)
# sources:
# my-bq:
# kind: bigquery
# project: PROJECT_ID
# tools:
# run_query:
# source: my-bq
# description: Run a read-only BigQuery query
# statement: SELECT ...
Package note (tested 2026-07-23): use
@toolbox-sdk/servervia npx — notpip install toolbox-core/uvx toolbox-core.toolbox-coreis the Python SDK library for building apps; it has no server CLI entry point.
| Server | Install | Use |
|---|---|---|
gcloud-mcp | npx @modelcontextprotocol/server-gcloud | Broad gcloud CLI coverage |
k8s-mcp | Standard k8s MCP server | Kubernetes API for GKE |
| Symptom | Likely Cause | Fix |
|---|---|---|
401 Unauthorized | ADC not set or expired | gcloud auth application-default login |
403 Permission Denied | SA missing required role | Add role per table above |
MCP server not found | Server not installed | Check install step in references/ |
| Connection timeout | VPC firewall blocking | Verify Private Google Access + firewall |