Skip to main content

Configuration

The Kubernetes Agent (k8s-autopilot) supports flexible configuration via environment variables and Docker Compose. This page details how to configure the agent for both local development and production usage.

1. Quick Start (Docker Compose)​

The recommended way to run k8s-autopilot is via Docker Compose. All 10 MCP servers (Helm, ArgoCD, Traefik, Argo Rollouts, Prometheus, Alertmanager, OpenTelemetry, Loki, Tempo, Kubernetes) run in-process via stdio transport — no sidecar containers needed.

You need two files: docker-compose.yml and .env.

Docker Compose​

services:
  k8s-autopilot:
    image: talkopsai/k8s-autopilot:latest
    container_name: k8s-autopilot
    ports:
      - "10102:10102"
    environment:
      # Required: API Keys (loaded from .env file)
      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
      - GOOGLE_GENAI_USE_VERTEXAI=${GOOGLE_GENAI_USE_VERTEXAI}

      # Github MCP Server Configuration
      - GITHUB_MCP_URL=${GITHUB_MCP_URL}
      - GITHUB_PERSONAL_ACCESS_TOKEN=${GITHUB_PERSONAL_ACCESS_TOKEN}
      - HELM_WORKSPACE=${HELM_WORKSPACE}

      # MCP Server Configuration (stdio in-process subprocesses)
      - >-
        MCP_SERVERS=[
        {"name": "github_mcp", "url": "https://api.githubcopilot.com/mcp/", "transport": "http", "disabled": false, "headers": {}, "auth_token_env_var": "GITHUB_PERSONAL_ACCESS_TOKEN"},
        {"name": "helm_mcp_server", "command": "helm-mcp-server", "transport": "stdio", "args": [], "env": {"MCP_ALLOW_WRITE": "true"}},
        {"name": "argocd_mcp_server", "command": "argocd-mcp-server", "transport": "stdio", "args": [], "env": {"MCP_ALLOW_WRITE": "true"}},
        {"name": "traefik_mcp_server", "command": "traefik-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "argo_rollout_mcp_server", "command": "argo-rollout-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "prometheus-mcp-server", "command": "prometheus-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "alertmanager-mcp-server", "command": "alertmanager-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "opentelemetry-mcp-server", "command": "opentelemetry-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "loki-mcp-server", "command": "loki-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "tempo-mcp-server", "command": "tempo-mcp-server", "transport": "stdio", "args": [], "env": {}},
        {"name": "kubernetes_mcp_server", "command": "kubernetes-mcp-server", "transport": "stdio", "args": []}
        ]

      # LLM Configuration
      - LLM_PROVIDER=${LLM_PROVIDER}
      - LLM_MODEL=${LLM_MODEL}
      - LLM_HIGHER_PROVIDER=${LLM_HIGHER_PROVIDER}
      - LLM_HIGHER_MODEL=${LLM_HIGHER_MODEL}
      - LLM_DEEPAGENT_PROVIDER=${LLM_DEEPAGENT_PROVIDER}
      - LLM_DEEPAGENT_MODEL=${LLM_DEEPAGENT_MODEL}

      # Logging & Kubeconfig
      - LOG_LEVEL=${LOG_LEVEL}
      - KUBECONFIG=/app/.kube/config

      # Observability: Prometheus
      - PROMETHEUS_BASE_URL=${PROMETHEUS_BASE_URL:-http://prometheus-operated.monitoring.svc:9090}
      - PROMETHEUS_VERIFY_SSL=${PROMETHEUS_VERIFY_SSL:-false}
      - PROMETHEUS_BACKEND_ID=${PROMETHEUS_BACKEND_ID:-default}

      # Observability: Alertmanager
      - ALERTMANAGER_BASE_URL=${ALERTMANAGER_BASE_URL:-http://alertmanager-operated.monitoring.svc:9093}
      - ALERTMANAGER_VERIFY_SSL=${ALERTMANAGER_VERIFY_SSL:-false}
      - AM_MAX_SILENCE_MINUTES=${AM_MAX_SILENCE_MINUTES:-1440}

      # Observability: Loki
      - LOKI_URL=${LOKI_URL:-http://loki.monitoring.svc:3100}
      - LOKI_ORG_ID=${LOKI_ORG_ID:-talkops}
      - LOKI_MAX_QUERY_BYTES=${LOKI_MAX_QUERY_BYTES:-5000000000}

      # Observability: Tempo
      - TEMPO_BASE_URL=${TEMPO_BASE_URL:-http://tempo.monitoring.svc:3200}
      - TEMPO_MAX_LOOKBACK=${TEMPO_MAX_LOOKBACK:-168h}
      - TEMPO_DEFAULT_SEARCH_LIMIT=${TEMPO_DEFAULT_SEARCH_LIMIT:-20}

      # Observability: OpenTelemetry
      - OTEL_CRD_GROUP=${OTEL_CRD_GROUP:-opentelemetry.io}
      - OTEL_CRD_API_VERSION=${OTEL_CRD_API_VERSION:-v1beta1}

      # ArgoCD
      - ARGOCD_SERVER_URL=${ARGOCD_SERVER_URL:-https://argocd-server.argocd.svc:443}
      - ARGOCD_AUTH_TOKEN=${ARGOCD_AUTH_TOKEN}
      - ARGOCD_INSECURE=${ARGOCD_INSECURE:-true}
    volumes:
      - ./workspace/helm-charts:/app/workspace/helm-charts
      - ${HOME}/.kube/config:/app/.kube/config:ro
    restart: unless-stopped
    networks:
      - k8s-autopilot-net

  talkops-ui:
    image: talkopsai/talkops:latest
    container_name: talkops-ui
    environment:
      - K8S_AGENT_URL=http://localhost:10102
      - TALKOPS_ENABLE_LOGGING=false
    ports:
      - "8080:80"
    depends_on:
      - k8s-autopilot
    restart: unless-stopped

networks:
  k8s-autopilot-net:
    driver: bridge

2. Environment Variables Reference​

LLM Provider Settings​

VariableDescriptionExample
LLM_PROVIDERDefault provider for standard model callsgoogle_genai, openai, anthropic
LLM_MODELDefault model for standard model callsgemini-2.5-flash, gpt-4o-mini
LLM_HIGHER_PROVIDERProvider for reasoning and routing tasksgoogle_genai, openai, anthropic
LLM_HIGHER_MODELModel for Supervisor routing & HITL plansgemini-3.1-pro-preview, gpt-5-mini
LLM_DEEPAGENT_PROVIDERProvider for coordinator deep agentsgoogle_genai, openai, anthropic
LLM_DEEPAGENT_MODELModel for complex code generationgemini-3.1-pro-preview, o4-mini

Observability MCP Configurations​

VariableDefaultPurpose
PROMETHEUS_BASE_URLhttp://prometheus:9090Prometheus API base endpoint
ALERTMANAGER_BASE_URLhttp://alertmanager:9093Alertmanager API base endpoint
LOKI_URLhttp://loki:3100Grafana Loki HTTP endpoint
LOKI_ORG_IDtalkopsMulti-tenant tenant ID
TEMPO_BASE_URLhttp://tempo:3200Grafana Tempo HTTP endpoint
OTEL_CRD_GROUPopentelemetry.ioKubernetes CRD group for OTel Operator