Telnyx MCP Server

# Prometheus alert rules for Telnyx MCP Server groups: - name: telnyx-mcp-server.rules rules: # Server availability alerts - alert: TelnyxMCPServerDown expr: up{job="telnyx-mcp-server"} == 0 for: 1m labels: severity: critical service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server is down" description: "The Telnyx MCP Server has been down for more than 1 minute." runbook_url: "https://wiki.company.com/runbooks/telnyx-mcp-server-down" - alert: TelnyxMCPServerHealthCheckFailing expr: up{job="telnyx-mcp-health"} == 0 for: 30s labels: severity: warning service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server health check failing" description: "The Telnyx MCP Server health endpoint is not responding." # Performance alerts - alert: TelnyxMCPHighResponseTime expr: http_request_duration_seconds{quantile="0.95"} > 5 for: 2m labels: severity: warning service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server high response time" description: "95th percentile response time is {{ $value }}s (threshold: 5s)" - alert: TelnyxMCPHighErrorRate expr: (rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m])) * 100 > 10 for: 2m labels: severity: critical service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server high error rate" description: "Error rate is {{ $value }}% (threshold: 10%)" # Resource utilization alerts - alert: TelnyxMCPHighMemoryUsage expr: process_resident_memory_bytes / (1024 * 1024) > 512 for: 5m labels: severity: warning service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server high memory usage" description: "Memory usage is {{ $value }}MB (threshold: 512MB)" - alert: TelnyxMCPHighCPUUsage expr: rate(process_cpu_seconds_total[5m]) * 100 > 80 for: 5m labels: severity: warning service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server high CPU usage" description: "CPU usage is {{ $value }}% (threshold: 80%)" # Connection and capacity alerts - alert: TelnyxMCPTooManyConnections expr: http_requests_active > 100 for: 1m labels: severity: warning service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server too many active connections" description: "Active connections: {{ $value }} (threshold: 100)" - alert: TelnyxMCPLowDiskSpace expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 10 for: 5m labels: severity: critical service: telnyx-mcp-server annotations: summary: "Telnyx MCP Server low disk space" description: "Disk space usage is {{ $value }}% (threshold: 90%)" # External dependency alerts - alert: TelnyxAPIUnreachable expr: probe_success{job="telnyx-api-probe"} == 0 for: 2m labels: severity: critical service: telnyx-mcp-server dependency: telnyx-api annotations: summary: "Telnyx API is unreachable" description: "Cannot reach Telnyx API from MCP server" - name: telnyx-mcp-server-sla.rules rules: # SLA tracking - record: telnyx_mcp_server:availability_1h expr: avg_over_time(up{job="telnyx-mcp-server"}[1h]) - record: telnyx_mcp_server:availability_24h expr: avg_over_time(up{job="telnyx-mcp-server"}[24h]) - record: telnyx_mcp_server:error_rate_5m expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) - record: telnyx_mcp_server:response_time_95p_5m expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) # SLA violation alerts - alert: TelnyxMCPSLAViolation expr: telnyx_mcp_server:availability_1h < 0.99 for: 0m labels: severity: critical service: telnyx-mcp-server sla: availability annotations: summary: "Telnyx MCP Server SLA violation" description: "Availability in the last hour: {{ $value | humanizePercentage }} (SLA: 99%)"