GCP Platform Engineer

platform-mcp

mcp-name: io.github.deBilla/platform-mcp

A read-only Model Context Protocol server that turns an AI agent (Claude Code, Claude Desktop, or any MCP client) into a GCP platform engineer. Point it at your Google Cloud projects and ask it to investigate incidents, take inventory, and surface cost-optimization opportunities — all without any ability to change your infrastructure.

Observation only. No tool in this server mutates state. Combined with a viewer-only identity (below), that gives you a hard, defense-in-depth guarantee that an agent can look but never touch.

What it can do

Typical prompts once it's connected:

• *"What are the top error groups in the last 24 hours, and which one is newest?"*
• *"Which GKE node pools are over-provisioned? Show mean CPU against machine type."*
• *"Where can I reduce spend in this project?"*

Multiple environments

One server can reach several projects. Define them under PLATFORM_MCP_ENVIRONMENTS (see Configuration) and the agent picks one from the wording of your prompt:

• *"Any errors in staging in the last hour?"*
• *"Compare Cloud Run services between staging and prod."*

Every tool takes an optional environment argument. Omit it and the default environment is used; pass environment="production" to target another. Names, any aliases you define, common shorthands (prod, stg, qa, …) and bare project ids all resolve. An unrecognized name is an error listing the valid options — a typo can never silently retarget the wrong project.

Each environment carries its own service account, so staging and production are reached through separate identities from the same process, and every result echoes back the environment and project it came from.

Requirements

• Python 3.11+
• A Google Cloud project and credentials (your own login, or a service account)
• The gcloud CLI for the one-time setup

Install

uvx platform-mcp          # no install step; uv fetches it on demand

pipx install platform-mcp # or keep it on PATH

From a checkout, for development:

git clone https://github.com/deBilla/platform-mcp.git

cd platform-mcp python3 -m venv .venv ./.venv/bin/pip install -e ".[dev]"

Check your setup

platform-mcp doctor

This checks, for every configured environment, that Application Default Credentials exist, that the read-only service account can be impersonated, that a real API read succeeds, and that the billing export is readable — printing the exact command to fix whatever fails. Run it before reporting a problem.

One-time GCP setup

Run these once per project you want to reach — staging and production each need their own APIs enabled and their own read-only service account.

1. Enable the APIs the tools depend on:

gcloud services enable \

logging.googleapis.com monitoring.googleapis.com clouderrorreporting.googleapis.com \ recommender.googleapis.com cloudasset.googleapis.com cloudbilling.googleapis.com \ bigquery.googleapis.com \ --project YOUR_PROJECT_ID

2. Grant read-only access to the identity the server runs as.

For local development with your own login (Application Default Credentials):

gcloud auth application-default login

The identity needs these viewer roles on the project, plus roles/billing.viewer on the billing account:

roles/viewer                # broad read (compute, run, gke, sql via Asset Inventory)

roles/logging.viewer roles/monitoring.viewer roles/errorreporting.viewer roles/recommender.viewer roles/cloudasset.viewer roles/bigquery.dataViewer # only for get_cost_breakdown roles/bigquery.jobUser # only for get_cost_breakdown

3. (Recommended) Use a dedicated read-only service account instead of your login. platform-mcp setup does every step below, is safe to re-run, and prints the config stanza at the end. It ships with the package, so there is nothing to clone:

uvx platform-mcp setup \

--project YOUR_PROJECT_ID \ --user you@example.com \ --billing-dataset YOUR_BILLING_PROJECT:billing # optional

Or by hand:

PROJECT=YOUR_PROJECT_ID

gcloud iam service-accounts create platform-mcp-ro \ --display-name "platform-mcp read-only" --project $PROJECT

SA=platform-mcp-ro@$PROJECT.iam.gserviceaccount.com for ROLE in roles/viewer roles/logging.viewer roles/monitoring.viewer \ roles/errorreporting.viewer roles/recommender.viewer roles/cloudasset.viewer \ roles/bigquery.jobUser; do gcloud projects add-iam-policy-binding $PROJECT \ --member="serviceAccount:$SA" --role="$ROLE" --condition=None done

Let your own login impersonate it (no key file to manage):

gcloud iam service-accounts add-iam-policy-binding $SA \ --member="user:you@example.com" \ --role="roles/iam.serviceAccountTokenCreator" --project $PROJECT

The grant everyone forgets. roles/bigquery.jobUser above only lets the account *start* a query; it grants no access to any data. A billing export almost always lives in a different project, so the account also needs read on that dataset. Without it get_cost_breakdown returns 403 while every other tool works, which reads like a bug in the tool rather than a missing grant:

bq add-iam-policy-binding \

--member="serviceAccount:$SA" --role=roles/bigquery.dataViewer \ YOUR_BILLING_PROJECT:billing

If you lack admin on the billing project, that one line is what to send to someone who has it. platform-mcp doctor checks it and says which side is missing.

Then reference it as that environment's impersonate value in PLATFORM_MCP_ENVIRONMENTS (preferred — no key file), or point at a downloaded key via GOOGLE_APPLICATION_CREDENTIALS.

Impersonation is performed by whatever identity your ADC resolves to. If your

ADC is itself an impersonated service account, that SA — not your user — needs

roles/iam.serviceAccountTokenCreator on each platform-mcp-ro.

Security model

Read-only is enforced by IAM, not by OAuth scope. The server requests the broad cloud-platform scope and stays read-only purely because it never calls a mutating API. Do not rely on the code alone — run it under a viewer-only identity (step 3 above) so the credential itself is incapable of writing, regardless of what code executes. This gives you two independent layers: the server doesn't try to write, and the identity couldn't if it did.

With multiple environments this stays per-project: each environment authenticates as its own service account, so a staging identity is never used to reach production. Grant each one viewer-only access to its project alone.

Configuration

The friendliest option is a config file, which keeps project ids and service account emails out of every client config you own:

mkdir -p ~/.config/platform-mcp

cp config.toml.example ~/.config/platform-mcp/config.toml $EDITOR ~/.config/platform-mcp/config.toml

With that in place, registering the server takes no environment variables at all. Point PLATFORM_MCP_CONFIG elsewhere to use a different file — a copy committed to your infrastructure repo, for instance.

Environment variables still work and always win over the file, so an existing setup keeps running unchanged and a one-off override needs no edit:

PLATFORM_MCP_ENVIRONMENTS holds a JSON object; each entry accepts:

A bare string value is shorthand for {"project": "..."}. As JSON inside .mcp.json the quotes must be escaped; unescaped it reads:

{

"staging": { "project": "my-app-staging", "impersonate": "platform-mcp-ro@my-app-staging.iam.gserviceaccount.com" }, "production": { "project": "my-app", "impersonate": "platform-mcp-ro@my-app.iam.gserviceaccount.com", "billing_export_table": "my-app.billing.gcp_billing_export_v1_XXXXXX" } }

Single-environment mode. If PLATFORM_MCP_ENVIRONMENTS is unset the server behaves as before, exposing one environment named default:

Register with a client

Claude Code — with a config file in place, this is the whole thing:

claude mcp add platform-mcp --scope user -- uvx platform-mcp

Claude Desktop — needs an absolute path to uvx; see Claude Desktop for the full walkthrough.

Without a config file, add the environment variables from .mcp.json.example to either form.

Skip the approval prompt

Every tool here is read-only, so approving each call individually adds nothing. Allow the whole server once, in Claude Code settings:

{ "permissions": { "allow": ["mcp__platform-mcp__*"] } }

The glob must sit after a literal mcp__ __ prefix — an unanchored pattern like mcp__* is ignored with a warning and approves nothing.

MCP Inspector — for interactive testing:

uvx --with 'mcp[cli]' mcp dev src/platform_mcp/server.py

Claude Desktop

Installing for a teammate who uses Claude Desktop rather than the CLI. It works the same as Claude Code, with one failure mode the CLI does not have.

Claude Desktop does not inherit your shell `PATH`. It launches from the Finder, so uvx and anything installed by Homebrew or uv are invisible to it. A config that says "command": "uvx" fails with ENOENT — the server never starts, and the error names the command rather than the reason. The command path must be absolute.

What does *not* break is credentials. Application Default Credentials are a file the Google libraries read directly, so gcloud is needed once, in a terminal, to create that file — not at runtime. The config file is found the same way, from the home directory, whatever launched the server.

Before you start: the admin grant

Each person impersonates the read-only service accounts, so an admin runs this once per person, per environment (the platform-mcp setup script does it for whoever runs it, but not for anyone else):

gcloud iam service-accounts add-iam-policy-binding \

platform-mcp-ro@YOUR_PROJECT_ID.iam.gserviceaccount.com \ --member="user:teammate@example.com" \ --role="roles/iam.ser