Connects Claude directly to Prometheus Alertmanager for querying and managing alerts without leaving your editor. Exposes 12 tools covering alert retrieval with filters, silence management, alert investigation, and correlation analysis to track down root causes. Ships as a native Go binary with built-in Kubernetes connectivity via client-go, so it can auto-connect to Alertmanager running in OpenShift clusters using the API proxy without port forwarding. Works via direct URL for standalone deployments or auto-detects kubeconfig for cluster environments. Useful when you're triaging incidents and want to query firing alerts, create silences, or investigate alert patterns conversationally instead of switching between the Alertmanager UI and your code.
A Model Context Protocol (MCP) server for Prometheus Alertmanager integration. Native Go binary with built-in Kubernetes connectivity via client-go.
npx -y mcp-alertmanager@latest
Add to your MCP client configuration (VS Code, Cursor, Windsurf, etc.):
{
"mcpServers": {
"alertmanager": {
"command": "npx",
"args": ["-y", "mcp-alertmanager@latest"],
"env": {
"ALERTMANAGER_URL": "http://localhost:9093"
}
}
}
}
code --add-mcp '{"name":"alertmanager","command":"npx","args":["-y","mcp-alertmanager@latest"],"env":{"ALERTMANAGER_URL":"http://localhost:9093"}}'
Automatically connects to Alertmanager 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/alertmanager-operated:9093
{
"mcpServers": {
"alertmanager": {
"command": "npx",
"args": ["-y", "mcp-alertmanager@latest"]
}
}
}
Download from GitHub Releases or build from source:
make build
./mcp-alertmanager
| Variable | Description |
|---|---|
ALERTMANAGER_URL | Direct Alertmanager API URL (overrides K8S auto-connect) |
| Flag | Description | Default |
|---|---|---|
--url | Direct Alertmanager URL | - |
--namespace | Kubernetes namespace | openshift-monitoring |
--service | Kubernetes service name | alertmanager-operated |
--service-port | Kubernetes service port | 9093 |
--service-scheme | Service scheme (http/https) | https |
--kubeconfig | Path to kubeconfig file | auto-detect |
Precedence: --url / ALERTMANAGER_URL > K8S auto-connect
Connection strategy:
--url or ALERTMANAGER_URL is set)| Tool | Description |
|---|---|
getAlerts | Get alerts with optional filters |
getAlertGroups | Get alerts grouped by routing labels |
getCriticalAlerts | Get critical severity alerts only |
getAlertingSummary | Summary: counts by severity, top alerts, namespaces |
| Tool | Description |
|---|---|
getSilences | List silences by state |
createSilence | Create a silence for an alert |
deleteSilence | Delete a silence by ID |
| Tool | Description |
|---|---|
getAlertmanagerStatus | Server status, version, cluster info |
getReceivers | List notification receivers |
| Tool | Description |
|---|---|
investigateAlert | Deep investigation of a specific alert |
getAlertHistory | Alert history and analysis guidance |
correlateAlerts | Find correlated alerts by shared labels |
"What alerts are currently firing?"
"Are there any critical alerts?"
"Give me a summary of the alerting status"
"Investigate the HighMemoryUsage alert"
"Create a 2-hour silence for PodCrashLooping"
"What receivers are configured?"
"Find correlated alerts to identify the root cause"
"Show me alert history for KubeNodeNotReady"
make build # Build for current platform
make build-all-platforms # Cross-compile for all platforms
podman build -f Containerfile -t mcp-alertmanager .
The container image is available on GitHub Container Registry:
ghcr.io/jeanlopezxyz/mcp-alertmanager:latest
Deploy using the included Helm chart:
# Add the chart repository (or use local chart)
helm upgrade --install mcp-alertmanager ./charts/mcp-alertmanager \
--namespace mcp-servers \
--create-namespace \
--set openshift=true
| Parameter | Description | Default |
|---|---|---|
image.registry | Container registry | ghcr.io |
image.repository | Image repository | jeanlopezxyz/mcp-alertmanager |
image.version | Image tag | latest |
openshift | Enable OpenShift Routes | false |
service.port | Service port | 8080 |
alertmanager.namespace | Alertmanager namespace | openshift-monitoring |
alertmanager.service | Alertmanager service name | alertmanager-operated |
rbac.useClusterReader | Use cluster-reader role | true |
helm upgrade --install mcp-alertmanager ./charts/mcp-alertmanager \
--namespace mcp-servers \
--set openshift=true \
--set alertmanager.url=http://alertmanager.monitoring:9093
io.github.infoinlet-marketplace/mcp-observability
betterdb-inc/monitor
com.mcparmory/datadog
thotischner/observability-mcp
io.github.tantiope/datadog-mcp
io.github.us-all/datadog