gcp-mcp-setup — Claude Code & Gemini CLI skill: what it does
gcp-mcp-setup — a skill for Claude Code, Codex, and Gemini CLI that wires up Google Managed MCP servers (OneMCP) to your CLI environment. It enables APIs, generates an API key, and writes the MCP config to the right settings file.
Apache-2.0 ★ 151 updated 2026-10-12
/plugin marketplace add gemini-cli-extensions/sre
/plugin install sre-extension@sreWhat gcp-mcp-setup does
The skill executes setup_onemcp.py, which enables Google Cloud APIs, provisions MCP servers, and writes the mcpServers block to your active harness config. The default set covers Logging, Monitoring, GKE, Run, Resource Manager, and Developer Knowledge. Pass --all to also bring in Error Reporting, Cloud SQL, Spanner, Pub/Sub, Vertex AI, Firestore, and BigQuery.
Where the config lands depends on the harness: Gemini CLI writes .gemini/settings.json locally or ~/.gemini/settings.json globally; Copilot CLI only writes to ~/.copilot/mcp-config.json with no workspace-level option. Use --harness gemini, --harness antigravity, or --harness copilot to target a specific one.
MCP servers authenticate through Application Default Credentials, not the gcloud auth login session. When these two identities differ, API calls fail with serviceusage.serviceUsageConsumer denied even if gcloud commands run fine. The verify_setup.py script checks identity consistency and confirms all expected google-* servers are registered.
What it helps with
- connect OneMCP to Gemini CLI in a single run
- provision MCP servers across multiple CLI harnesses at once
- auto-generate an API key and write the config file
- add Vertex AI and BigQuery via the
--allflag - diagnose a mismatch between gcloud and ADC identities
Example prompts for the agent
- Set up OneMCP for project
my-gcp-projecttargeting the Gemini CLI harness - Run gcp-mcp-setup with
--allto include Firestore and BigQuery - Verify all
google-*MCP servers are registered after setup in Codex
How to install gcp-mcp-setup
1Plugin marketplace
/plugin marketplace add gemini-cli-extensions/sre/plugin install sre-extension@sreThis installs the whole sre-extension plugin with all its skills
2Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill gcp-mcp-setup -a claude-code3Manually: put the files in place
~/.claude/skills/gcp-mcp-setup/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gcp-mcp-setup/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill gcp-mcp-setup -a codex2Manually: put the files in place
.agents/skills/gcp-mcp-setup/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill gcp-mcp-setup -a cursor2Manually: put the files in place
.cursor/skills/gcp-mcp-setup/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gemini-cli-extensions/sre skills/gcp-mcp-setup2Manually: put the files in place
.github/skills/gcp-mcp-setup/SKILL.md1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill gcp-mcp-setup -a gemini-cli2Platform CLI
gemini skills install https://github.com/gemini-cli-extensions/sre --path skills/gcp-mcp-setupManually: put the files in place
.devin/skills/gcp-mcp-setup/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gcp-mcp-setup
How do I install gcp-mcp-setup in Claude Code?
Run /plugin marketplace add gemini-cli-extensions/sre, then /plugin install sre-extension@sre. You can also use npx skills add gemini-cli-extensions/sre --skill gcp-mcp-setup -a claude-code, which places the skill at ~/.claude/skills/gcp-mcp-setup/SKILL.md.
What does gcp-mcp-setup do?
It runs a setup script that enables the required Google Cloud APIs, provisions Google Managed MCP servers, and writes the mcpServers configuration block to the settings file for your chosen CLI harness.
Why do MCP servers fail even though gcloud commands work?
MCP servers use Application Default Credentials rather than your gcloud auth login session. Run gcloud auth application-default login --account <PROPOSED_IDENTITY_EMAIL> to align the two identities, then re-run verify_setup.py to confirm.
Source text
SKILL.md · Apache-2.0
---
name: gcp-mcp-setup
description: 🐉 Use when the user wants to set up Google Managed MCP (OneMCP) servers for their CLI environment. Automates enabling services, MCP servers, generating API keys, and configuring the MCP settings file for the active harness (Gemini, Antigravity, or Copilot CLI).
metadata:
author: Riccardo
version: 0.0.10
status: published
---
# OneMCP Setup Skill
## Overview
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.
## When to Use
Use this skill when the user asks to "install OneMCP", "setup OneMCP", or "configure Google Managed MCP servers".
## Core Pattern
1. **Prerequisites Verification**: Ensure the user has `gcloud` authenticated and a target Google Cloud Project with billing enabled.
2. **Setup Script Execution**: Run the provided script to enable APIs, MCP services, and generate the required API Key.
- By default, it installs a **Lean SRE toolset** (Logging, Monitoring, GKE, Run, Resource Manager, Developer Knowledge).
- Use the `--all` flag to include optional services (Error Reporting, Databases, Vertex AI).
- Use `--harness` to target a specific CLI harness (`gemini`, `antigravity`, or `copilot`). Defaults to `gemini+antigravity`.
- Script: `skills/gcp-mcp-setup/scripts/setup_onemcp.py <PROJECT_ID> [--local | --global] [--harness {gemini,antigravity,copilot}] [--all] [--google-maps-key YOUR_KEY]`
3. **Configure Settings**: The script automatically writes the `mcpServers` configuration to the correct location depending on the target harness:
- **Gemini CLI**: `.gemini/settings.json` (local) or `~/.gemini/settings.json` (global).
- **Antigravity CLI (agy)**: `.gemini/antigravity/mcp_config.json` and `.gemini/config/mcp_config.json` (local) or the global equivalents under `~/.gemini/`.
- **GitHub Copilot CLI**: `~/.copilot/mcp-config.json` (always global — no workspace-level config yet).
4. **Verification & Diagnostics:**
- Script: `skills/gcp-mcp-setup/scripts/verify_setup.py [--harness {gemini,antigravity,copilot}]`
- This script checks identity consistency (gcloud vs ADC), runs the harness-specific MCP list command, and confirms all expected google-* servers are registered.
## Examples
User: "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."
## Authentication
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, you can propose to run this on user's behalf: `gcloud auth application-default login --account <PROPOSED_IDENTITY_EMAIL>`
### 💡 Path Forward
If you encounter an identity mismatch:
1. Run `gcloud auth application-default login --account=YOUR_CLI_IDENTITY` to synchronize identities.
2. Verify the identities match by running the verification script: `python3 skills/gcp-mcp-setup/scripts/verify_setup.py`.
## Documentation
- Antigravity MCP integration guide: https://antigravity.google/docs/mcp
- Code samples from Romin Irani: https://github.com/rominirani/google-mcp-servers/blob/main/demos/README.md
- All supported products: https://docs.cloud.google.com/mcp/supported-products
© Riccardo · Apache-2.0 · gemini-cli-extensions/sre