gcp-cloud-monitoring
GCP Cloud Monitoring
MCP Server
- Endpoint:
https://monitoring.googleapis.com/mcp(Streamable HTTP) - Auth: OAuth 2.0 via Google IAM — service account key (
GOOGLE_APPLICATION_CREDENTIALS) orgcloud auth application-default login - Requires:
GCP_PROJECT_IDenvironment variable
Available Tools (6)
| Tool | What It Does |
|---|---|
list_timeseries |
Query time series data — CPU, memory, network, disk metrics for any GCP resource |
list_metric_descriptors |
Discover available metric types in a project — find what you can monitor |
list_alert_policies |
List all alerting policies — conditions, notification channels, thresholds |
get_alert_policy |
Get details of a specific alerting policy |
list_alerts |
List current and past alert violations — what's firing right now |
get_alert |
Get details of a specific alert violation |
Workflow: GCP Network Monitoring
When a user asks "how is our GCP network performing?":
- Check alerts:
list_alertsto find any active alert violations - VM network metrics:
list_timeseriesforcompute.googleapis.com/instance/network/received_bytes_countandsent_bytes_count - Packet drops:
list_timeseriesforcompute.googleapis.com/instance/network/received_packets_dropped_count - Firewall metrics:
list_timeseriesforcompute.googleapis.com/firewall/dropped_packets_count - Load balancer metrics:
list_timeseriesforloadbalancing.googleapis.com/https/request_countandtotal_latencies - Report: Network health dashboard with any issues flagged
Workflow: Alert Investigation
When investigating GCP alerts:
- List active alerts:
list_alerts— find what's currently firing - Get alert details:
get_alert— condition, threshold, resource affected - Get policy:
get_alert_policy— what triggers this alert, notification channels - Pull metrics:
list_timeseriesfor the affected metric — see the spike/anomaly - Cross-reference: Use
gcp-cloud-loggingfor correlated log entries - Report: Alert investigation with root cause and timeline
Workflow: Resource Health Check
When checking GCP infrastructure health:
- Discover metrics:
list_metric_descriptorsfiltered by service (compute, networking, loadbalancing) - VM CPU/Memory:
list_timeseriesforcompute.googleapis.com/instance/cpu/utilizationand memory metrics - Disk I/O:
list_timeseriesforcompute.googleapis.com/instance/disk/read_bytes_countand write metrics - Network throughput:
list_timeseriesfor network sent/received bytes - Alert status:
list_alert_policies+list_alerts— any policies in violation? - Report: Infrastructure health dashboard with severity ratings
Common GCP Network Metrics
| Metric | What It Tells You |
|---|---|
compute.googleapis.com/instance/network/received_bytes_count |
Inbound network throughput per VM |
compute.googleapis.com/instance/network/sent_bytes_count |
Outbound network throughput per VM |
compute.googleapis.com/instance/network/received_packets_dropped_count |
Dropped inbound packets (congestion) |
compute.googleapis.com/instance/network/sent_packets_dropped_count |
Dropped outbound packets (congestion) |
compute.googleapis.com/firewall/dropped_packets_count |
Packets dropped by VPC firewall rules |
loadbalancing.googleapis.com/https/request_count |
HTTP(S) LB request rate |
loadbalancing.googleapis.com/https/total_latencies |
HTTP(S) LB end-to-end latency |
loadbalancing.googleapis.com/https/backend_latencies |
Backend response time behind LB |
vpn.googleapis.com/tunnel_established |
Cloud VPN tunnel state (1=up, 0=down) |
vpn.googleapis.com/sent_bytes_count |
Bytes sent through VPN tunnel |
router.googleapis.com/bgp/received_routes_count |
BGP routes received by Cloud Router |
interconnect.googleapis.com/link/received_bytes_count |
Cloud Interconnect link throughput |
Important Rules
- Remote MCP server — hosted by Google, no local install needed
- OAuth 2.0 authentication — uses IAM for access control
- Project-scoped — metrics are scoped to the configured GCP project
- Read-only — monitoring queries don't modify anything
- Record in GAIT — log monitoring investigations for audit trail
Environment Variables
GCP_PROJECT_ID— Google Cloud project IDGOOGLE_APPLICATION_CREDENTIALS— Path to service account key JSON file
More from automateyournetwork/netclaw
pyats-topology
Network topology discovery via CDP/LLDP neighbors, ARP tables, routing peers, and interface mapping to build complete network maps. Use when mapping the network, building a diagram, discovering what is connected to what, or documenting device neighbors and links.
20drawio-diagram
Generate draw.io network diagrams — native .drawio files with CLI export (PNG/SVG/PDF), plus browser-based Mermaid/XML/CSV via MCP server. Use when creating network topology diagrams, generating architecture visuals, exporting diagrams to PNG or PDF, or building draw.io files from discovery data.
19aws-architecture-diagram
AWS architecture diagrams — generate visual network topology diagrams from live AWS infrastructure. Use when drawing AWS network diagrams, visualizing VPCs, mapping Transit Gateway topology, or generating architecture documentation.
19grafana-observability
Grafana observability platform — dashboards, Prometheus PromQL, Loki LogQL, alerting, incidents, OnCall schedules, annotations, datasource queries, panel rendering (75+ tools). Use when querying Grafana dashboards, running PromQL for interface metrics, searching Loki logs for syslog events, investigating firing alerts, or checking who is on call.
18pyats-health-check
Comprehensive network device health monitoring - CPU, memory, interfaces, hardware, NTP, logging, environment, and uptime analysis. Use when running a device health check, monitoring CPU or memory usage, checking interface errors, or validating NTP sync.
17aws-security-audit
AWS security auditing — IAM users/roles/policies, CloudTrail API events, security posture analysis. Use when auditing IAM permissions, investigating security incidents, checking MFA compliance, or tracing API activity in CloudTrail.
16