PrometheusSAFE
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/users/pab1it0/packages/container/package/prometheus-mcp-server) [](https://github.com/pab1it0/prometheus-mcp-server/pkgs/container/charts%2Fprometheus-mcp-server) [](https://github.com/pab1it0/prometheus-mcp-server/releases) [](https://codecov.io/gh/pab1it0/prometheus-mcp-server) [](https://github.com/pab1it0/prometheus-mcp-server/blob/main/LICENSE)
Give AI assistants the power to query your Prometheus metrics.
A [Model Context Protocol][mcp] (MCP) server that provides access to your Prometheus metrics and queries through standardized MCP interfaces, allowing AI assistants to execute PromQL queries and analyze your metrics data.
[mcp]: https://modelcontextprotocol.io
Getting Started
Prerequisites
- Prometheus server accessible from your environment
- MCP-compatible client (Claude Desktop, VS Code, Cursor, Windsurf, etc.)
Installation Methods
Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"prometheus": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PROMETHEUS_URL",
"ghcr.io/pab1it0/prometheus-mcp-server:latest"
],
"env": {
"PROMETHEUS_URL": ""
}
}
}
}Claude Code
Install via the Claude Code CLI:
claude mcp add prometheus --env PROMETH
b57fd679f4abOBSERVED · 2026-09-29Connect
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 prometheus-mcp-server:1.6.2 --env PROMETHEUS_PASSWORD=${PROMETHEUS_PASSWORD} --env PROMETHEUS_TOKEN=${PROMETHEUS_TOKEN} -- docker run -i --rm ghcr.io/pab1it0/prometheus-mcp-server:1.6.2:NoneTrust 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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
.env.template
.helmignore
The MCP endpoint will be available at `http://127.0.0.1:8080/sse`.
http://127.0.0.1:{{ .Values.service.port }}/sseconfig.url_ssl_verify = False # Ensure SSL verification is disabled
curl -LsSf https://astral.sh/uv/install.sh | sh
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
b57fd679f4abfull audit observations/trust-audit/mcp-server/pab1it0__prometheus-1.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 |
|---|---|---|---|---|---|
| 2026-09-29 | b57fd679f4ab | SAFE | B | 89 | first audit |
Questions
What is the Prometheus MCP server?
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
Is Prometheus 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.
What credentials does Prometheus need?
It reads PROMETHEUS_CLIENT_KEY, PROMETHEUS_PASSWORD and PROMETHEUS_TOKEN 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 Prometheus run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on PyPI as prometheus_mcp_server.
How current is this page?
The grade is for one exact copy of the source (b57fd679f4ab), read on 2026-09-29. The repository is watched and re-audited when it changes.