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).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
k8s_get_podsB

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

k8s_describe_podB

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

k8s_delete_podA

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

k8s_get_pod_logsC

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

k8s_get_eventsC

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

k8s_top_podsA

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

k8s_top_nodesA

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

k8s_get_deploymentsB

List deployments with replica status, strategy, and age

k8s_rollout_statusC

Check the rollout status of a deployment

k8s_rollback_deploymentC

Rollback a deployment to the previous revision

k8s_scale_deploymentC

Scale a deployment to a specified number of replicas

k8s_get_servicesB

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

k8s_get_nodesA

List all cluster nodes with status, roles, and version

k8s_describe_nodeB

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

k8s_cordon_nodeA

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

k8s_uncordon_nodeA

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

docker_list_containersB

List Docker containers with their status, image, and ports

docker_inspect_containerC

Get detailed information about a Docker container

docker_container_logsC

Fetch logs from a Docker container

docker_container_statsC

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

docker_list_imagesB

List local Docker images with repository, tag, and size

docker_inspect_imageC

Get detailed information about a Docker image

docker_compose_psC

Show status of Docker Compose services

docker_compose_logsB

Show logs from Docker Compose services

docker_list_networksB

List Docker networks with driver and scope

docker_inspect_networkA

Get detailed info about a Docker network including connected containers

prom_instant_queryC

Execute a PromQL instant query and return current values

prom_range_queryB

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

prom_active_alertsA

List all currently firing Prometheus alerts

prom_alert_rulesA

List all Prometheus alert rules and their current state

prom_targetsB

Show Prometheus scrape target health status

terraform_planA

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

terraform_state_listB

List all resources in the Terraform state

terraform_state_showB

Show details of a specific resource in Terraform state

terraform_outputB

Read Terraform output values

terraform_validateC

Validate Terraform configuration and check formatting

security_trivy_scanC

Scan a container image for vulnerabilities using Trivy

security_gitleaks_scanC

Scan a directory for leaked secrets and credentials using Gitleaks

security_k8s_auditB

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

system_disk_usageC

Show disk usage for the system or a specific path

system_processesC

List top processes sorted by CPU or memory usage

system_network_connectionsC

Show active network connections and listening ports

system_logsC

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