Provides tools for querying Prometheus metrics, including instant and range queries, scrape targets, alerting rules, cluster health diagnostics, node and namespace diagnosis, top resource consumers, and pod investigation.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
A Model Context Protocol (MCP) server for Prometheus integration. Native Go binary with built-in Kubernetes connectivity via client-go.
npx -y mcp-prometheus@latestAdd to your MCP client configuration (VS Code, Cursor, Windsurf, etc.):
{
"mcpServers": {
"prometheus": {
"command": "npx",
"args": ["-y", "mcp-prometheus@latest"],
"env": {
"PROMETHEUS_URL": "http://localhost:9090"
}
}
}
}code --add-mcp '{"name":"prometheus","command":"npx","args":["-y","mcp-prometheus@latest"],"env":{"PROMETHEUS_URL":"http://localhost:9090"}}'Automatically connects to Prometheus running in OpenShift/Kubernetes via the K8S API service proxy. Uses native kubeconfig/in-cluster config via client-go. No kubectl or port-forwarding required.
Default: openshift-monitoring/prometheus-operated:9090
{
"mcpServers": {
"prometheus": {
"command": "npx",
"args": ["-y", "mcp-prometheus@latest"]
}
}
}Download from GitHub Releases or build from source:
make build
./mcp-prometheusRelated MCP server: Prometheus MCP Server
Variable | Description |
| Direct Prometheus API URL (overrides K8S auto-connect) |
Flag | Description | Default |
| Direct Prometheus URL | - |
| Kubernetes namespace |
|
| Kubernetes service name |
|
| Kubernetes service port |
|
| Service scheme (http/https) |
|
| Path to kubeconfig file | auto-detect |
Precedence: --url / PROMETHEUS_URL > K8S auto-connect
Connection strategy:
Direct URL (if --url or PROMETHEUS_URL is set)
K8S API proxy (auto-detect kubeconfig or in-cluster config)
Tool | Description |
| Execute a PromQL instant query |
| Execute a PromQL range query over time |
| Get scrape targets status |
| Get alerting and recording rules |
| Get server version and runtime info |
Tool | Description |
| Comprehensive cluster health overview |
| Diagnose a specific node's health |
| Diagnose a namespace's health |
Tool | Description |
| Top CPU/memory/network consumers |
| Deep investigation of a specific pod |
| Compare metrics between two time periods |
"What's the current CPU usage across all nodes?"
"Show me the cluster health overview"
"Which pods are using the most memory?"
"Diagnose node worker-1"
"Are all scrape targets healthy?"
"Compare CPU usage now vs 24 hours ago"
"Investigate pod my-app in namespace production"
"What alerting rules are defined?"make build # Build for current platform
make build-all-platforms # Cross-compile for all platformspodman build -f Containerfile -t mcp-prometheus .The container image is available on GitHub Container Registry:
ghcr.io/jeanlopezxyz/mcp-prometheus:latestDeploy using the included Helm chart:
# Add the chart repository (or use local chart)
helm upgrade --install mcp-prometheus ./charts/mcp-prometheus \
--namespace mcp-servers \
--create-namespace \
--set openshift=trueParameter | Description | Default |
| Container registry |
|
| Image repository |
|
| Image tag |
|
| Enable OpenShift Routes |
|
| Service port |
|
| Prometheus namespace |
|
| Prometheus service name |
|
| Use cluster-reader role |
|
helm upgrade --install mcp-prometheus ./charts/mcp-prometheus \
--namespace mcp-servers \
--set openshift=true \
--set prometheus.url=http://prometheus.monitoring:9090Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Query your app's logs, metrics and incidents from your AI assistant.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
Query, explore, and manage your databases through natural conversation.
Ask your databases questions in plain English, run read-only SQL and set up data alerts.