mcpField
M
mcp-alertmanager

mcp-alertmanager

Local
github.com/jeanlopezxyzCloud & Infra0Updated 38w ago

About mcp-alertmanager

mcp-alertmanager is a Go MCP server for operating Prometheus Alertmanager, aimed at monitoring and platform teams. It provides alert, silence, status, and troubleshooting tools, with direct URL or Kubernetes connectivity.

Key features

  1. 01Filter and group alerts
  2. 02Create and delete silences
  3. 03Inspect status and receivers
  4. 04Investigate and correlate alerts

Use cases

  1. 01Review active or critical alerts
  2. 02Silence an alert during maintenance
  3. 03Trace related alerts during an incident

MCP support

Exposes 12 Alertmanager tools to MCP clients, including alert queries, silence management, status checks, and investigation. Connects through a direct API URL or the Kubernetes API service proxy.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"jeanlopezxyz-mcp-alertmanager": {
"command": "npx",
"args": [
"-y",
"mcp-alertmanager"
]
}
}
}
Run commandnpx -y mcp-alertmanager

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-alertmanager2.1.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Alertmanager MCP Server (Go)

License: MIT npm version Go GitHub release

A Model Context Protocol (MCP) server for Prometheus Alertmanager integration. Native Go binary with built-in Kubernetes connectivity via client-go.

Installation

npx
npx -y mcp-alertmanager@latest
MCP Client Configuration

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"
      }
    }
  }
}
VS Code
code --add-mcp '{"name":"alertmanager","command":"npx","args":["-y","mcp-alertmanager@latest"],"env":{"ALERTMANAGER_URL":"http://localhost:9093"}}'
Kubernetes Auto-Connect

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"]
    }
  }
}
Binary

Download from GitHub Releases or build from source:

make build
./mcp-alertmanager

Configuration

Environment Variables
VariableDescription
ALERTMANAGER_URLDirect Alertmanager API URL (overrides K8S auto-connect)
CLI Flags
FlagDescriptionDefault
--urlDirect Alertmanager URL-
--namespaceKubernetes namespaceopenshift-monitoring
--serviceKubernetes service namealertmanager-operated
--service-portKubernetes service port9093
--service-schemeService scheme (http/https)https
--kubeconfigPath to kubeconfig fileauto-detect

Precedence: --url / ALERTMANAGER_URL > K8S auto-connect

Connection strategy:

  1. Direct URL (if --url or ALERTMANAGER_URL is set)
  2. K8S API proxy (auto-detect kubeconfig or in-cluster config)

Tools (12)

Alerts
ToolDescription
getAlertsGet alerts with optional filters
getAlertGroupsGet alerts grouped by routing labels
getCriticalAlertsGet critical severity alerts only
getAlertingSummarySummary: counts by severity, top alerts, namespaces
Silences
ToolDescription
getSilencesList silences by state
createSilenceCreate a silence for an alert
deleteSilenceDelete a silence by ID
Status
ToolDescription
getAlertmanagerStatusServer status, version, cluster info
getReceiversList notification receivers
Troubleshooting
ToolDescription
investigateAlertDeep investigation of a specific alert
getAlertHistoryAlert history and analysis guidance
correlateAlertsFind correlated alerts by shared labels

Example Prompts

"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"

Development

Build
make build              # Build for current platform
make build-all-platforms # Cross-compile for all platforms
Container
podman build -f Containerfile -t mcp-alertmanager .

Kubernetes / OpenShift Deployment

Container Image

The container image is available on GitHub Container Registry:

ghcr.io/jeanlopezxyz/mcp-alertmanager:latest
Helm Chart

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
Helm Values
ParameterDescriptionDefault
image.registryContainer registryghcr.io
image.repositoryImage repositoryjeanlopezxyz/mcp-alertmanager
image.versionImage taglatest
openshiftEnable OpenShift Routesfalse
service.portService port8080
alertmanager.namespaceAlertmanager namespaceopenshift-monitoring
alertmanager.serviceAlertmanager service namealertmanager-operated
rbac.useClusterReaderUse cluster-reader roletrue
Example with custom Alertmanager
helm upgrade --install mcp-alertmanager ./charts/mcp-alertmanager \
  --namespace mcp-servers \
  --set openshift=true \
  --set alertmanager.url=http://alertmanager.monitoring:9093

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.