GCP Platform Engineer MCP Server

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. It runs locally over stdio via the published package.

People who work with devops, finops and gcp and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-02 · ★ 2 · #63 OF 120 MAINTAINED DEVOPS & MONITORING · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install GCP Platform Engineer

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add debilla-platform-mcp -- uvx platform-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "debilla-platform-mcp": {
      "command": "uvx",
      "args": [
        "platform-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-07-20 - young repo, little track record yet

license MIT - declared in the repository

pypi package platform-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.deBilla is GitHub-verified and matches the repo owner

03 · What GCP Platform Engineer can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Limitations (from the README)

- All tools cap result counts and truncate long payloads to stay token-friendly. - GCP clients are built lazily and cached per environment, so switching between staging and production mid-conversation costs one client construction each. - Cost recommenders are zonal/regional; list_cost_recommendations auto-discovers the locations where you have resources (via Asset Inventory) and fans out, skipping locations and reco

04 · Who maintains GCP Platform Engineer

GCP Platform Engineer is maintained by debilla. We track 2 MCP servers from debilla - 2 actively maintained, 2 combined GitHub stars, oldest repo from Jun 2026.

05 · Facts

repository: github.com/debilla/platform-mcp
website: https://debilla.github.io/platform-mcp/
category: DevOps & monitoring - ranked #63 of 120 actively-maintained DevOps & monitoring servers as of 2026-09-18.
registry: io.github.deBilla/platform-mcp (active, first published 2026-08-30 · 2 versions)
packages: pypi:platform-mcp

06 · GCP Platform Engineer FAQ

What is GCP Platform Engineer?

Is GCP Platform Engineer still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-02. We re-verify nightly.

How do I install GCP Platform Engineer?

Run `uvx platform-mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does GCP Platform Engineer run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to GCP Platform Engineer

Alternatives to GCP Platform Engineer

Maintained DevOps & monitoring servers if GCP Platform Engineer isn't the fit.

Pairs well with

Servers that cover what GCP Platform Engineer doesn't - only shown when the pairing reason fits the companion.

More DevOps & monitoring MCP servers · Process · Dynatrace · Dynatrace Managed MCP · Taskbounty Check · Go Model

More Python MCP servers · Calendar MCP · Deep Mem · Deepsky Aviation Regulations · Defenter Proxy · Fiscal Brasil (dehor-labs) · see all