Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KUBECONFIGNoPath to the Kubernetes configuration file (e.g., ~/.kube/config).
PROMETHEUS_URLNoThe URL of the Prometheus server (e.g., http://localhost:9090).

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
k8s_get_pods

List pods in a Kubernetes namespace with their status, restarts, and age

k8s_describe_pod

Get detailed information about a specific pod including containers, resources, and events

k8s_delete_pod

Delete a specific pod (it will be recreated if managed by a controller)

k8s_get_pod_logs

Fetch logs from a pod with options for tail lines, time range, and container selection

k8s_get_events

List cluster events filtered by namespace and type (Normal/Warning)

k8s_top_pods

Show CPU and memory usage for pods (requires metrics-server)

k8s_top_nodes

Show CPU and memory usage for all cluster nodes (requires metrics-server)

k8s_get_deployments

List deployments with replica status, strategy, and age

k8s_rollout_status

Check the rollout status of a deployment

k8s_rollback_deployment

Rollback a deployment to the previous revision

k8s_scale_deployment

Scale a deployment to a specified number of replicas

k8s_get_services

List services with type, cluster IP, ports, and age

k8s_get_nodes

List all cluster nodes with status, roles, and version

k8s_describe_node

Get detailed node info including capacity, allocatable resources, conditions, and taints

k8s_cordon_node

Mark a node as unschedulable (cordon) — prevents new pods from being scheduled

k8s_uncordon_node

Mark a node as schedulable (uncordon) — re-enables pod scheduling

docker_list_containers

List Docker containers with their status, image, and ports

docker_inspect_container

Get detailed information about a Docker container

docker_container_logs

Fetch logs from a Docker container

docker_container_stats

Get real-time CPU, memory, and network stats for a container

docker_list_images

List local Docker images with repository, tag, and size

docker_inspect_image

Get detailed information about a Docker image

docker_compose_ps

Show status of Docker Compose services

docker_compose_logs

Show logs from Docker Compose services

docker_list_networks

List Docker networks with driver and scope

docker_inspect_network

Get detailed info about a Docker network including connected containers

prom_instant_query

Execute a PromQL instant query and return current values

prom_range_query

Execute a PromQL query over a time range and return series data

prom_active_alerts

List all currently firing Prometheus alerts

prom_alert_rules

List all Prometheus alert rules and their current state

prom_targets

Show Prometheus scrape target health status

terraform_plan

Run terraform plan to preview infrastructure changes (read-only, safe)

terraform_state_list

List all resources in the Terraform state

terraform_state_show

Show details of a specific resource in Terraform state

terraform_output

Read Terraform output values

terraform_validate

Validate Terraform configuration and check formatting

security_trivy_scan

Scan a container image for vulnerabilities using Trivy

security_gitleaks_scan

Scan a directory for leaked secrets and credentials using Gitleaks

security_k8s_audit

Audit Kubernetes namespace for security misconfigurations (privileged containers, missing limits, RBAC issues)

system_disk_usage

Show disk usage for the system or a specific path

system_processes

List top processes sorted by CPU or memory usage

system_network_connections

Show active network connections and listening ports

system_logs

Read system logs from journalctl or a log file

Prompts

Interactive templates invoked by user choice

NameDescription
troubleshootSystematic troubleshooting workflow for infrastructure issues — guides you through gathering context, identifying anomalies, and suggesting fixes
capacity-planCapacity planning analysis — assess current resource usage, identify bottlenecks, and recommend scaling
security-auditInfrastructure security review — check for common security misconfigurations and vulnerabilities

Resources

Contextual data attached and managed by the client

NameDescription
Kubernetes Cluster InfoCurrent cluster overview: context, nodes, namespaces, running pods count
Service Health StatusHealth status of all services with endpoint readiness and deployment status
Infrastructure SummaryFull infrastructure summary: K8s cluster, Docker, Prometheus status

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/batu-sonmez/infraclaude'

If you have feedback or need assistance with the MCP directory API, please join our Discord server