gcloud-mcp

Provides an MCP (Model Context Protocol) server that lets AI assistants interact with Google Cloud via the gcloud CLI (and the repo also lists additional MCP servers for observability, storage, and backupdr). The gcloud server exposes tools such as running gcloud commands; some commands may be restricted by agent permissions.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Infrastructure mcp google-cloud gcloud agent-tools automation infrastructure
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
58
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
60
Error Messages
0
Auth Simplicity
55
Rate Limits
10

🔒 Security

TLS Enforcement
85
Auth Strength
60
Scope Granularity
40
Dep. Hygiene
50
Secret Handling
50

Security posture at the MCP layer is not fully specified in the provided README excerpt. The server relies on the gcloud CLI and therefore inherits IAM permissions. The README indicates some commands may be restricted by agent permissions (a positive safety control), but it does not document fine-grained auth/scopes at the MCP protocol level, secret-handling practices, or explicit operational safeguards (e.g., confirmation steps for destructive actions, structured permission model details).

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
35
Error Recovery
25
AF Security Reliability

Best When

You want an MCP-capable client (Gemini CLI, Claude Desktop, Cursor, Cline, VS Code MCP) to safely mediate gcloud operations using predefined tools and permissions.

Avoid When

You cannot control or restrict what commands the agent can run, or you require strongly documented operational characteristics like retries/pagination/error codes at the MCP layer.

Use Cases

  • Natural-language execution of gcloud CLI tasks (e.g., create/list/describe resources) through an MCP client
  • Automating multi-step Google Cloud workflows by chaining multiple MCP tool calls
  • Enabling non-expert users to manage Google Cloud via constrained agent tooling

Not For

  • Direct unattended autonomous execution of high-risk gcloud commands without operator oversight
  • Use cases requiring a public HTTP/REST API for programmatic integration (this is primarily an MCP/CLI-driven tool server)
  • Environments where you cannot grant appropriate Google Cloud credentials/permissions

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Google Cloud credentials used by gcloud CLI (implied by prerequisite/CLI-based execution)
OAuth: No Scopes: No

README shows integration via npx and indicates gcloud CLI is required. It does not detail MCP-specific auth (e.g., OAuth, tokens, scopes) at the MCP server protocol level; authentication is likely inherited from the gcloud CLI credentials configured in the environment.

Pricing

Free tier: No
Requires CC: No

Pricing for the npm package/hosting service is not described in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tool execution may be restricted by MCP permissions for certain gcloud commands; agents may fail or need different prompts when restricted.
  • Since commands run via gcloud CLI, operations are subject to the permissions and configuration of the underlying gcloud credentials in the runtime environment.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for gcloud-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered