Log inSubmit server
GCP Platform Engineer logo

GCP Platform Engineer

Read-only GCP diagnostics, resource inventory, monitoring, billing, and cost recommendations through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install GCP Platform Engineer

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "gcp-platform-engineer": {
      "command": "uvx",
      "args": [
        "platform-mcp"
      ],
      "env": {
        "PLATFORM_MCP_CONFIG": "YOUR_VALUE_HERE",
        "PLATFORM_MCP_ENVIRONMENTS": "YOUR_VALUE_HERE",
        "PLATFORM_MCP_DEFAULT_ENVIRONMENT": "YOUR_VALUE_HERE",
        "GOOGLE_APPLICATION_CREDENTIALS": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

The GCP Platform Engineer MCP server connects AI agents to Google Cloud projects for read-only incident investigation, inventory checks, and cost analysis. It queries Cloud Logging, Error Reporting, Cloud Monitoring, BigQuery billing exports, Cloud Asset Inventory, and selected Compute, Cloud Run, GKE, and Cloud SQL resources. Configure one or more environments with separate identities, then target them by name, alias, shorthand, or project ID. Reach for it when an agent needs operational visibility without infrastructure mutation.

Use cases

  • Investigate recent production errors and grouped application failures
  • Compare monitoring data across staging and production environments
  • Inventory Cloud Run, GKE, Compute Engine, and Cloud SQL resources
  • Find billing trends and project-level cost contributors
  • Surface idle, rightsizing, and other GCP recommendations

Key features

  • Read-only Google Cloud access
  • Multi-environment project targeting
  • Cloud Logging and Error Reporting queries
  • Cloud Monitoring metrics and alert inspection
  • BigQuery billing and cost recommendation analysis
  • Cloud Asset and managed-service inventory

Tools16

What GCP Platform Engineer lets your agent do. Expand a tool for its parameters.

Verified live~3.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 42d

What it can do

From the 16 tools this server returned when we ran it; 16 declare their own safety hints.

Makes network requests · 15Read-only tools · 16
Network at startup2 connections
Files written at startup30

Observed 2026-10-16 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8h ago via OSV.dev · platform-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Tools exposed16Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How GCP Platform Engineer works

What GCP Platform Engineer does

The GCP Platform Engineer MCP server gives an MCP client read-only access to selected Google Cloud platform data. It is intended for the Cloud Platforms category and supports incident investigation, service inventory, monitoring review, billing analysis, and recommendation discovery without exposing tools that change infrastructure.

The server can query Cloud Logging with advanced filters, retrieve recent high-severity entries, and group application errors from Error Reporting. It can also inspect Monitoring time series, alert policies, and uptime checks. For inventory work, it searches Cloud Asset Inventory and lists Compute Engine instances, Cloud Run services, GKE clusters, and Cloud SQL instances.

Cost-focused tools read billing export data from BigQuery, report linked billing-account status, and collect cost-optimization or service-specific recommendations. Results can be scoped to a configured project or, for billing analysis, expanded to the full billing account.

How it works

A single GCP Platform Engineer MCP server can be configured with multiple environments, such as staging and production. Each environment identifies a project and can use its own service account through impersonation or a credentials file. Tool calls accept an optional environment value; omitted values use the configured default.

Environment names, configured aliases, common shorthand names, and bare project IDs can resolve to the target project. Invalid names produce an error rather than silently selecting another project. Responses include the environment and project associated with the result, which helps distinguish data from multiple targets.

All capabilities are observational. The recommended security model combines the server's read-only behavior with viewer-oriented IAM permissions on the identity it uses. This limits the effect of both the available tools and the credentials behind them.

Setup and configuration

The GCP Platform Engineer MCP server requires Python 3.11 or newer, a Google Cloud project, credentials, and the gcloud CLI for initial setup. It can be run with uvx platform-mcp, installed with pipx, or installed from a checkout for development.

Before connecting a client, enable the APIs used by the selected tools, including Logging, Monitoring, Error Reporting, Recommender, Cloud Asset, Cloud Billing, and BigQuery. Grant the identity appropriate viewer roles. Cost breakdowns additionally require BigQuery job and dataset access, and a configured fully qualified billing export table.

Configuration can be stored in a TOML file or supplied through environment variables. PLATFORM_MCP_CONFIG selects an alternate configuration file. PLATFORM_MCP_ENVIRONMENTS defines projects, impersonated service accounts, aliases, and billing export settings, while PLATFORM_MCP_DEFAULT_ENVIRONMENT selects the fallback target. GOOGLE_APPLICATION_CREDENTIALS provides an alternative service-account key path.

Run platform-mcp doctor to check credentials, impersonation, API access, and billing-export readability for configured environments.

Tools and capabilities

The GCP Platform Engineer MCP server exposes tools for:

  • Selecting and inspecting configured environments.
  • Filtering logs and retrieving recent errors.
  • Grouping Error Reporting issues by frequency and service.
  • Querying metric time series with configurable windows, alignment, and aggregation.
  • Listing alert policies and uptime checks.
  • Reviewing billing totals by service, SKU, project, or region.
  • Finding idle, rightsizing, IAM, and other available recommendations through GCP recommenders.
  • Searching assets and listing common compute and managed-service resources.

Query limits, lookback periods, locations, services, metric filters, and environment targets vary by tool. Cost recommendation discovery can scan specified locations or derive locations from Asset Inventory.

Limitations and notes

The server does not mutate GCP state. It also does not replace IAM configuration: the caller must provide credentials with access to each target project and, where applicable, the billing dataset and account.

Billing data depends on a readable BigQuery export. A billing export may cover several projects, so account-wide results must be requested deliberately when comparing projects. Some recommendation locations or recommenders may be unavailable or empty and are skipped during aggregate scans.

Large asset searches and broad log or metric queries can consume substantial context. Use filters and limits when the question concerns a particular service, time range, resource type, or location.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about GCP Platform Engineer

GCP Platform Engineer is an MCP server that connects AI agents to Google Cloud projects through read-only tools for logs, errors, metrics, alerts, billing, recommendations, and resource inventory. It supports multiple configured environments, including separate staging and production identities, so agents can investigate operations without changing infrastructure.

Install it with `uvx platform-mcp` or `pipx install platform-mcp`. For development, clone the repository and install its package in a virtual environment. Configure Google Cloud credentials and environments before registering the server with an MCP client.

Configure multiple projects through `PLATFORM_MCP_ENVIRONMENTS` or the platform-mcp TOML configuration file. Each environment specifies a project and can specify its own impersonated read-only service account, aliases, and billing export table. Use `PLATFORM_MCP_DEFAULT_ENVIRONMENT` to choose the fallback.

Run `platform-mcp doctor` to check billing-export readability and identify missing access. The identity needs BigQuery job access on the project and data-viewer access on the billing export dataset, which may be in a different project. A billing export table must also be configured.

Yes. The README names Claude Desktop and Claude Code as supported MCP clients. The server is also described as usable with any MCP client, provided the client can register and run the configured MCP server.

Related MCP servers

All in Cloud Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewGCP Platform Engineer AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/gcp-platform-engineer?style=directory)](https://allmcps.com/mcp/gcp-platform-engineer)
HTML Embed
<a href="https://allmcps.com/mcp/gcp-platform-engineer"><img src="https://allmcps.com/api/badge/gcp-platform-engineer?style=directory" alt="GCP Platform Engineer on AllMCPs" /></a>