Skip to main content
Glama
mcp-server-devops
by Feliper83

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KUBECONFIGNoPath to a kubeconfig file to query a real cluster.
MCP_GRAFANA_URLNoBase URL of a Grafana instance.
MCP_K8S_IN_CLUSTERNoSet (any value) to use in-cluster service account auth instead of a kubeconfig.
MCP_PROMETHEUS_URLNoBase URL of a Prometheus server, e.g. https://prometheus.internal.
MCP_GRAFANA_API_KEYNoGrafana API key / service account token.
MCP_PROMETHEUS_TOKENNoOptional bearer token for authenticated Prometheus instances.

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
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
k8s_pod_statusA

List pod status (phase, readiness, restarts, node) for a Kubernetes cluster. Connects to a real cluster when KUBECONFIG or MCP_K8S_IN_CLUSTER is set; otherwise returns realistic mock data for a telecom provisioning platform so the tool is demoable without infra.

prometheus_queryA

Run a PromQL instant query against Prometheus. Connects to a real Prometheus instance when MCP_PROMETHEUS_URL is set (optionally MCP_PROMETHEUS_TOKEN for bearer auth); otherwise returns mock latency/error-rate/resource metrics so the tool is demoable without infra.

grafana_dashboard_summaryA

Fetch a Grafana dashboard's title and panel list by UID. Connects to a real Grafana instance when MCP_GRAFANA_URL and MCP_GRAFANA_API_KEY are set; otherwise returns mock dashboards ("telecom-provisioning", "k8s-cluster-overview") so the tool is demoable without infra.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a clearly distinct system and data type: Kubernetes pod status, Prometheus metrics, and Grafana dashboards. There is no realistic scenario where an agent would confuse one for another.

Naming Consistency4/5

All names are snake_case and include a product/resource prefix, but the patterns vary slightly: k8s_pod_status and grafana_dashboard_summary are noun phrases while prometheus_query uses a product_action form. The deviation is minor and still highly readable.

Tool Count3/5

Three tools is technically within the reasonable 3-15 range, but for a server labeled 'devops' the surface feels thin and narrow, covering only observability reads. More operational breadth would justify the server name better.

Completeness2/5

The surface is limited to read-only observability: pod status, a PromQL query, and a dashboard summary. There are significant gaps for a DevOps server, including logs, deployments, services, events, alerting, and any write or remediation operations.

Maintenance

ActivityMaintained
ResponsivenessOutdated data