Skip to content

Home

Jump to bottom
Anna edited this page Jun 25, 2026 · 2 revisions

Aura Tracker GCP

An open-source Model Context Protocol server that gives LLMs structured, safe access to your Google Cloud Platform infrastructure.

Safe by default — no configuration required:

  • Read-only out of the box. 67 of 69 tools are pure reads. The two write operations require explicit human confirmation before anything changes in GCP.
  • No surprise bills. All paid GCP APIs (RECOMMENDER_ENABLED) are disabled by default. Standard read APIs count against your existing project quota only.
  • Human-in-the-loop for mutations. A two-step confirmation gate is enforced at the server level — the LLM cannot bypass it.

→ Full details: Safety & Cost Safeguards

Why Aura Tracker GCP?

Managing distributed GCP infrastructure requires juggling the Cloud Console, gcloud CLI, and dozens of service-specific APIs. When something goes wrong at 2 AM, piecing together logs, metrics, IAM bindings, and traffic splits across ten browser tabs is slow and error-prone.

Aura Tracker GCP is a bridge. It exposes 67 read and write operations across 26 GCP service modules as MCP tools. Connect it to Claude Desktop (or any MCP-compatible host) and ask in plain language:

"Which Cloud Run services have an Aura Score below 50 and what's causing it?" "Show me the Pub/Sub topics with unacknowledged message lag above 10,000." "Scale the api-gateway node pool from 3 to 5 nodes — but show me a preview first."

The LLM calls the right tools, assembles the answer, and — for any mutation — requires your explicit confirmation before touching anything.

The Problem

GCP's complexity grows non-linearly with team size. A medium project might have:

  • 15+ Cloud Run services across 3 regions
  • GKE clusters with 40+ workloads
  • Dozens of Pub/Sub topics wired to Eventarc triggers and Workflows
  • IAM bindings spread across hundreds of resources
  • Observability gaps you don't know exist yet

Finding which service is responsible for a latency spike — tracing it from Cloud Trace through IAM to a Pub/Sub subscription — requires cross-product context a human has to assemble manually.

The Solution

┌──────────────────────────────────────────────────────┐
│  You (natural language)                              │
│         ↓                                            │
│  LLM (Claude, GPT-4o, …)                            │
│         ↓  MCP tool calls                            │
│  Aura Tracker GCP  ←──────────────→  GCP APIs       │
│         ↓                                            │
│  Structured answer + safety confirmation             │
└──────────────────────────────────────────────────────┘

The server runs locally (or on Cloud Run in SSE mode). It authenticates to GCP using your existing Application Default Credentials or a service account key. No data ever leaves your environment — the LLM calls tools, Aura Tracker GCP fetches from GCP, returns results to the LLM. That's the entire data path.

Quick Start (3 Steps)

1. Install

Homebrew (macOS / Linux) — recommended

brew install asbrodova/tap/aura-tracker-gcp

Direct binary download (all platforms)

Download the archive for your platform from the latest release, extract, and place the binary on your PATH.

# macOS Apple Silicon example
curl -L https://github.com/asbrodova/aura-tracker-gcp/releases/latest/download/aura-tracker-gcp_darwin_arm64.tar.gz \
  | tar xz
sudo mv aura-tracker-gcp /usr/local/bin/

Building from source, Go toolchain install, and Docker usage are covered in Getting Started.

2. Authenticate with GCP

gcloud auth application-default login

3. Connect to Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "aura-tracker-gcp": {
      "command": "aura-tracker-gcp",
      "env": {
        "GCP_PROJECT_ID": "my-project"
      }
    }
  }
}

Restart Claude Desktop. Try: "List my Cloud Run services."

What's Included

Category Tools Highlights
Compute GKE (4), Cloud Run (6), Functions (2) Aura Score, bottleneck detection
Data Cloud SQL, Spanner, AlloyDB, Firestore, Memorystore Read-only inventory
Messaging Pub/Sub (3), Eventarc (2), Scheduler (1), Workflows (2), Tasks (1) Health + lag inspection
Networking Load Balancers, VPC, NEGs, API Gateway, PSC 7 tools
Observability Monitoring (8), Logging (1), Coverage (1) SLOs, traces, alerts, coverage gaps
Architecture Topology (1), Serverless Graph (1), Architecture Graph (2) Full project graph export
IAM Permissions test, bindings, service accounts 3 tools
Supply Chain Artifact Registry, Cloud Build, Service Directory 4 tools
Advanced GKE Workloads (5), GKE Mesh (1), Tagging (1) Kubernetes-level visibility

69 tools total. Full reference: Module Reference

Wiki Navigation

Page What it covers
Safety & Cost Safeguards Default safety posture, no-surprise-bill guarantee, HITL confirmation
Getting Started Prerequisites, install, auth, first query, module selection
Configure Your Environment All env vars, --modules flag, SSE mode
Security and Safety PII scrubbing, IAM least-privilege guide
Managing GCP Costs Paid APIs, billing alerts
Built-in Prompts and Workflows audit-security-posture, optimize-bigquery-costs, incident-response-helper
MCP Resources Reference 10 built-in resources (BigQuery, Cloud Run, Storage, IAM)
Module Reference Index of all 26 module pages
Architecture and Contributing Hexagonal architecture, adding tools

Clone this wiki locally