Security MCP Server

# ============================================================================= # Prometheus Configuration for MCP Server # ============================================================================= # Metrics collection and monitoring configuration # ============================================================================= # ----------------------------------------------------------------------------- # Global Configuration # ----------------------------------------------------------------------------- global: # How frequently to scrape targets scrape_interval: 15s # How frequently to evaluate rules evaluation_interval: 15s # Scrape timeout scrape_timeout: 10s # External labels to attach to metrics external_labels: monitor: 'mcp-monitor' environment: 'production' region: 'us-east-1' # ----------------------------------------------------------------------------- # Alertmanager Configuration # ----------------------------------------------------------------------------- alerting: alertmanagers: - static_configs: - targets: # - 'alertmanager:9093' # Timeout for sending alerts timeout: 10s # Path prefix for Alertmanager path_prefix: /alertmanager # ----------------------------------------------------------------------------- # Rule Files # ----------------------------------------------------------------------------- rule_files: - '/etc/prometheus/alerts.yml' # - '/etc/prometheus/recording_rules.yml' # ----------------------------------------------------------------------------- # Scrape Configurations # ----------------------------------------------------------------------------- scrape_configs: # --------------------------------------------------------------------------- # Prometheus Self-Monitoring # --------------------------------------------------------------------------- - job_name: 'prometheus' static_configs: - targets: ['localhost:9090'] metrics_path: /metrics scrape_interval: 10s # Metadata labels relabel_configs: - source_labels: [__address__] target_label: instance replacement: 'prometheus' # --------------------------------------------------------------------------- # MCP Server Metrics # --------------------------------------------------------------------------- - job_name: 'mcp-server' static_configs: - targets: ['mcp-server:9090'] metrics_path: /metrics scrape_interval: 15s scrape_timeout: 10s # Add custom labels relabel_configs: - source_labels: [__address__] target_label: instance replacement: 'mcp-server-primary' - target_label: service replacement: 'mcp' - target_label: component replacement: 'server' # Metric relabeling metric_relabel_configs: # Drop debug metrics in production - source_labels: [__name__] regex: 'debug_.*' action: drop # Keep only important metrics - source_labels: [__name__] regex: '(mcp_tool_execution_.*|mcp_health_.*|mcp_circuit_breaker_.*|up)' action: keep # --------------------------------------------------------------------------- # Node Exporter (Host Metrics) # --------------------------------------------------------------------------- - job_name: 'node-exporter' static_configs: - targets: ['node-exporter:9100'] scrape_interval: 30s relabel_configs: - source_labels: [__address__] target_label: instance replacement: 'docker-host' - target_label: job replacement: 'node' # --------------------------------------------------------------------------- # cAdvisor (Container Metrics) # --------------------------------------------------------------------------- - job_name: 'cadvisor' static_configs: - targets: ['cadvisor:8080'] scrape_interval: 30s # Container-specific relabeling metric_relabel_configs: # Extract container name - source_labels: [container_label_com_docker_compose_service] target_label: service # Keep only relevant container metrics - source_labels: [__name__] regex: 'container_(cpu|memory|network|disk)_.*' action: keep # Drop metrics for pause containers - source_labels: [container_name] regex: 'POD|pause' action: drop # --------------------------------------------------------------------------- # Grafana Metrics (Optional) # --------------------------------------------------------------------------- - job_name: 'grafana' static_configs: - targets: ['grafana:3000'] metrics_path: /metrics scrape_interval: 30s relabel_configs: - source_labels: [__address__] target_label: instance replacement: 'grafana' # --------------------------------------------------------------------------- # Service Discovery for Docker Swarm (Optional) # --------------------------------------------------------------------------- # - job_name: 'docker-swarm' # dockerswarm_sd_configs: # - host: unix:///var/run/docker.sock # role: tasks # # relabel_configs: # # Only keep containers with prometheus labels # - source_labels: [__meta_docker_container_label_prometheus_io_scrape] # regex: 'true' # action: keep # # # Use container label for job name # - source_labels: [__meta_docker_container_label_prometheus_io_job] # target_label: job # # # Use container name as instance # - source_labels: [__meta_docker_container_name] # target_label: instance # --------------------------------------------------------------------------- # DNS Service Discovery (Optional) # --------------------------------------------------------------------------- # - job_name: 'dns-discovery' # dns_sd_configs: # - names: # - '_prometheus._tcp.mcp.local' # type: 'SRV' # refresh_interval: 30s # ----------------------------------------------------------------------------- # Remote Write Configuration (Optional) # ----------------------------------------------------------------------------- # remote_write: # - url: 'https://prometheus-remote.example.com/api/v1/write' # remote_timeout: 30s # write_relabel_configs: # - source_labels: [__name__] # regex: 'mcp_.*' # action: keep # queue_config: # capacity: 10000 # max_shards: 5 # max_samples_per_send: 1000 # ----------------------------------------------------------------------------- # Remote Read Configuration (Optional) # ----------------------------------------------------------------------------- # remote_read: # - url: 'https://prometheus-remote.example.com/api/v1/read' # read_recent: true # ----------------------------------------------------------------------------- # Storage Configuration # ----------------------------------------------------------------------------- # storage: # tsdb: # retention: # time: 30d # size: 10GB