$ timeahead.in
/servers/blog/about
/ servers/npm/@google-cloud/observability-mcp
npm

@google-cloud/observability-mcp

MCP Server for GCP environment for interacting with various Observability APIs.

★ 819 stars↓ 15k/wkupdated 1d agogithub ↗
☆ Watch this server📋 Install guide⚡ Compare⚑ Claim listing
90good
▣ Overview
gcloud-mcp Servers CILicenseVersionVersionVersionVersion

What it does

This MCP server exposes Google Cloud Observability APIs through thirteen tools, enabling Claude and other AI assistants to query logs, metrics, and traces from GCP projects using natural language. Instead of constructing complex API calls or memorizing gcloud command syntax, you describe what telemetry you need and the server retrieves it from Cloud Logging, Cloud Monitoring, and Cloud Trace. The assistant can analyze patterns, drill into incidents, and construct multi-step troubleshooting workflows without leaving the conversation.

Who it's for

Developers, SREs, and platform engineers who operate applications on Google Cloud and use AI assistants in their incident-response or debugging workflows. Best suited for teams already running Claude in their development environment who want rapid observability access during outages or performance investigations.

Common use cases

  • Query application logs across multiple GCP projects to identify error patterns or root causes
  • Fetch and analyze metrics to assess resource usage and system performance
  • Search Cloud Trace data to pinpoint latency bottlenecks in microservices
  • Retrieve audit logs for compliance checks or deployment troubleshooting

Setup pitfalls

  • Requires gcloud CLI installed locally; Node.js and npm alone are insufficient for GCP authentication
  • Needs Node.js 20 or later; earlier versions will fail
  • Must authenticate with GCP using gcloud auth application-default login and have appropriate IAM roles for Observability APIs (Logs Reader, Monitoring Reader, Trace Reader)
  • CI is currently failing; test stability in your environment before relying on it for critical workflows
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
100
35.0
Freshness
25%
100
25.0
Adoption
20%
79
15.8
Quality
10%
90
9.0
Trust
10%
50
5.0
Total
89.8
⚿ Capabilities & Risk Explainer
fs readfs writenetworkexecsecrets
◆ Risk level: high· 13 tools · auth: API key
fs read + fs write + network + exec + secrets active — can execute code, access credentials, and make external network calls.
Tool nameDescriptionDestructive?
list_log_entries✓ no
list_log_names✓ no
list_buckets✓ no
list_views✓ no
list_sinks✓ no
+8 more tools
list_log_scopes✓ no
list_metric_descriptors✓ no
list_time_series✓ no
list_alert_policies✓ no
list_alerts✓ no
list_traces✓ no
get_trace✓ no
list_group_stats✓ no
⚙ Install config
Claude Desktop · Cursor · Windsurf · VS Code (Copilot) · Claude Code
add to your MCP client config:
{
  "mcpServers": {
    "google-cloudobservability": {
      "command": "npx",
      "args": [
        "-y",
        "@google-cloud/observability-mcp"
      ]
    }
  }
}
📈 Score historylast 30 snapshots
4/30/20266/6/2026 · 30 snapshots
⚙ Maintenance health
72/ 100 · is this project alive?
contributors (1y)18
top contributor share25%
releases (1y)26
last release30d ago
ci⚠ failing
⛁ Raw data
weekly downloads15k
github stars819
forks73
open issues44
license✓ present
readme length20053 chars
last publish0d ago
last commit1d ago
last updated7h ago
install verified✗ fail · 22d ago
owner of this server? claim your listing to get a verified badgeclaim →
🔔 Score drop alerts
get notified by email when this server's score drops 5+ points