> For the complete documentation index, see [llms.txt](https://docs.natoma.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.natoma.ai/apps/prometheus.md).

# Prometheus

**Type:** Official

**Source Type:** Local Package

**Source:** [PyPI](https://pypi.org/project/awslabs-prometheus-mcp-server/)

**Description:** Prometheus MCP server (AWS Managed Prometheus) provides AI assistants with access to your AWS Managed Prometheus workspace. It enables running PromQL queries, listing metrics, and inspecting workspace metadata using AWS SigV4 authentication.

**Configuration Parameters:**

* **AWS Region** \* - AWS region for the Prometheus workspace (e.g. `us-east-1`).
* **Workspace URL** (optional) - AWS Managed Prometheus workspace URL.
* **AWS Profile** (optional) - Name of an AWS CLI profile on the host (preferred).
* **AWS Access Key ID** (sensitive) (optional) - Use only with **AWS Secret Access Key** for static-key auth.
* **AWS Secret Access Key** (sensitive) (optional) - Pair with **AWS Access Key ID**.
* **AWS Session Token** (sensitive) (optional) - Optional — for STS temporary credentials.

**Setup Steps:**

1. In the AWS console, navigate to **Amazon Managed Service for Prometheus → Workspaces** and note the workspace URL and region.
2. Decide how the server will authenticate: AWS profile (preferred), static keys, or temporary STS credentials.
3. When creating the connection in Natoma, fill in the region (and either the profile or the access keys) and save.