// 🐉 [SRE] Use when the user wants to set up Google Managed MCP (OneMCP) servers for their Gemini CLI environment. Automates enabling services, MCP servers, generating API keys, and configuring ~/.gemini/settings.json.
| name | gcp-mcp-setup |
| description | 🐉 [SRE] Use when the user wants to set up Google Managed MCP (OneMCP) servers for their Gemini CLI environment. Automates enabling services, MCP servers, generating API keys, and configuring ~/.gemini/settings.json. |
| metadata | {"author":"Riccardo","version":"0.0.9","status":"published"} |
This skill provides the automated steps to configure your environment and enable the Core Google Managed MCP servers (Logging, Monitoring, GKE, Run, Resource Manager, Developer Knowledge) by default. Use the --all flag to include additional services like Error Reporting, Cloud SQL, Spanner, Pub/Sub, Vertex AI, Firestore, and BigQuery.
Use this skill when the user asks to "install OneMCP", "setup OneMCP", or "configure Google Managed MCP servers".
gcloud authenticated and a target Google Cloud Project with billing enabled.--all flag to include optional services (Error Reporting, Databases, Vertex AI).skills/gcp-mcp-setup/scripts/setup_onemcp.py <PROJECT_ID> [--local | --global] [--all] [--google-maps-key YOUR_KEY]mcpServers configuration to the correct location depending on which harness/CLI you are running:
.gemini/settings.json (if --local is provided) or ~/.gemini/settings.json (if --global is provided)..gemini/antigravity/mcp_config.json and .gemini/config/mcp_config.json (if --local is provided) or the global equivalents under ~/.gemini/ (if --global is provided).skills/gcp-mcp-setup/scripts/verify_setup.pyskills/gcp-mcp-setup/scripts/test_mcp_endpoint.sh [ENDPOINT_URL]./skills/gcp-mcp-setup/scripts/test_mcp_endpoint.sh https://monitoring.googleapis.com/mcpUser: "Please install OneMCP on my project my-gcp-project" Agent: "I will use the gcp-mcp-setup skill to configure your project and Gemini settings for Cloud Logging, Developer Knowledge, Firestore, and BigQuery."
Note that the gcloud CLI Identity (how you are currently logged in via gcloud auth login) may differ from the MCP Server Identity (which is based on Application Default Credentials, or ADC).
MCP servers typically use ADC to authenticate. If these identities do not match, you may encounter permission errors (e.g., serviceusage.serviceUsageConsumer denied) even if gcloud commands work correctly.
If MCP doesn't work, yhou can poropose to run this on user's behalf: gcloud auth application-default login --account <PROPOSED_IDENTITY_EMAIL>
If you encounter an identity mismatch:
gcloud auth application-default login --account=YOUR_CLI_IDENTITY to synchronize identities.python3 skills/gcp-mcp-setup/scripts/verify_setup.py.🐉 Detects anomalies in time-series data from various sources.
🐉 Skill for interacting with and analyzing Google Cloud Logging and Error Reporting. Use this when you need to process large JSON logs from GCP or convert them to Apache format for easier analysis.
🐉 Fetches and parses time-series data from various sources.
🐉 [SRE] Use when you need to follow established SRE playbooks for GCP/GKE investigations, including infrastructure discovery and common mitigation steps.
🐉 Initial Google Cloud environment verification and authentication setup. Use when starting a new session to ensure correct identities across gcloud, ADC, and kubectl.
🐉 [SRE] Manage Service Level Objectives (SLOs) on Google Cloud. Use when you need to discover Monitoring Services, list existing SLOs, or create new SLOs (Availability/Latency) via the REST API when gcloud commands are unavailable.