AlertmanagerSAFE
A Model Context Protocol (MCP) server that enables AI assistants to integreate with Prometheus Alertmanager
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Prometheus Alertmanager MCP
Table of Contents
- Table of Contents
- 1. Introduction
- 2. Features
- 3. Quickstart
- 3.1. Prerequisites
- 3.2. Installing via Smithery
- 3.3. Local Run
- 3.4. Docker Run
- 4. Tools
- 5. Development
- 6. License
1. Introduction
Prometheus Alertmanager MCP is a Model Context Protocol (MCP) server for Prometheus Alertmanager. It enables AI assistants and tools to query and manage Alertmanager resources programmatically and securely.
2. Features
- [x] Query Alertmanager status, alerts, silences, receivers, and alert groups
- [x] Smart pagination support to prevent LLM context window overflow when handling large numbers of alerts
- [x] Create, update, and delete silences
- [x] Create new alerts
- [x] Authentication support (Basic auth via environment variables)
- [x] Multi-tenant support (via
ALERTMANAGER_TENANTfor Mimir/Cortex) - [x] Docker containerization support
3. Quickstart
3.1. Prerequisites
- Python 3.12+
- uv (for fast dependency management).
- Docker (optional, for containerized deployment).
- Ensure your Prometheus Alertmanager server is accessible from the environment where you'll run this MCP server.
3.2. Installing via Smi
9fab2da658bfOBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add alertmanager_mcp_server --env ALERTMANAGER_PASSWORD=${ALERTMANAGER_PASSWORD} --env MCP_API_KEY=${MCP_API_KEY} -- uvx alertmanager_mcp_server{
"mcpServers": {
"alertmanager_mcp_server": {
"command": "uvx",
"args": [
"alertmanager_mcp_server"
],
"env": {
"ALERTMANAGER_PASSWORD": "${ALERTMANAGER_PASSWORD}",
"MCP_API_KEY": "${MCP_API_KEY}"
}
}
}
}Exposed tools (8)
5 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_silence | destructive | Delete a silence by its ID |
get_alert_groups | read | Get a list of alert groups |
get_alerts | read | Get a list of alerts currently in Alertmanager. |
get_silence | read | Get a silence by its ID |
get_silences | read | Get list of all silences |
get_status | read | Get current status of an Alertmanager instance and its cluster |
post_alerts | write | Create new alerts |
post_silence | write | Post a new silence or update an existing one |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
delete_silence
.env.sample
- MCP_API_KEY: **Optional** bearer/API key. When set, every `http`/`sse` request must send `Authorization: Bearer <key>` or it is rejected with `401`. When unset, the server logs a startup warning tha
Gates applied: no_behavioural_pass.
9fab2da658bffull audit observations/trust-audit/mcp-server/ntk148v__alertmanager.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 9fab2da658bf | SAFE | B | 89 | first audit |
Questions
What is the Alertmanager MCP server?
A Model Context Protocol (MCP) server that enables AI assistants to integreate with Prometheus Alertmanager
What tools does Alertmanager expose?
8 in total: 5 read-only, 2 that write, and 1 that can delete or overwrite (delete_silence). Every one is listed on this page with its risk.
Is Alertmanager safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Alertmanager need?
It reads ALERTMANAGER_PASSWORD and MCP_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Alertmanager run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as alertmanager_mcp_server.
How current is this page?
The grade is for one exact copy of the source (9fab2da658bf), read on 2026-10-09. The repository is watched and re-audited when it changes.