
Mcp Alertmanager
io.github.jeanlopezxyzPublished by GitHub account jeanlopezxyzv2.1.1Updated Oct 24, 2026
A Model Context Protocol (MCP) server for Prometheus Alertmanager
Overview
An MCP server for Prometheus Alertmanager that lets an assistant read alerts, inspect silences and receivers, and create or delete silences.
- What you can do
- Query alerts, including grouped, critical-only and summary views with severity counts and namespaces.List and manage silences: view by state, create a silence for an alert, or delete one by ID. Check Alertmanager status, version, cluster info and configured notification receivers. Investigate a specific alert, review alert history and find correlated alerts by shared labels.
- When to use it
- Useful when you run Prometheus Alertmanager, directly or in OpenShift/Kubernetes, and want an assistant to triage firing alerts, summarize alerting state, or set and clear silences during an incident.
- Requirements
- A local runtime for the npm package (run via npx) or the Go binary. Access to an Alertmanager endpoint, either through the ALERTMANAGER_URL environment variable or the --url flag, or Kubernetes auto-connect using a kubeconfig or in-cluster config with access to the alertmanager service.
Installation
In SourceWeft
- Open Mcp Alertmanager in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
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
MCP Client Configuration
Add to your MCP client configuration (VS Code, Cursor, Windsurf, etc.):
VS Code
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
Binary
Download from GitHub Releases or build from source:
Configuration
Environment Variables
CLI Flags
Precedence: --url / ALERTMANAGER_URL > K8S auto-connect
Connection strategy:
- Direct URL (if
--urlorALERTMANAGER_URLis set) - K8S API proxy (auto-detect kubeconfig or in-cluster config)
Tools (12)
Alerts
Silences
Status
Troubleshooting
Example Prompts
Development
Build
Container
Kubernetes / OpenShift Deployment
Container Image
The container image is available on GitHub Container Registry:
Helm Chart
Deploy using the included Helm chart:
Helm Values
Example with custom Alertmanager
License
Source: README.md at commit 649cf0d
Tools
0Version history
1- v2.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts