--- title: "AWS Managed Prometheus MCP: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/mcp-servers/awslabs-prometheus/ description: "Pins the AWS Labs server for PromQL against Amazon Managed Prometheus, and records that the basic Kiro example omits the workspace URL." --- # AWS Managed Prometheus MCP: review, setup & limitations · Undominated.ai > Pins the AWS Labs server for PromQL against Amazon Managed Prometheus, and records that the basic Kiro example omits the workspace URL. [← Explore all mcp servers](/mcp-servers/) OBSERVABILITY / AWS Labs # AWS Managed Prometheus MCP Pins the AWS Labs server for PromQL against Amazon Managed Prometheus, and records that the basic Kiro example omits the workspace URL. [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp/tree/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server) SOURCE REVIEW Reviewed 2026-10-14 Evidence 2 linked sources Publisher AWS Labs Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/LICENSE) Revision 8840003820a7 [Read what was—and wasn’t—checked ↓](#review) “Runs instant and range PromQL against AWS Managed Prometheus with SigV4, and lists workspaces and metric names.” [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/README.md) Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - The catalogue has a Prometheus MCP server from another publisher and not this AWS Managed Prometheus server. - The README shows both a minimal uvx config and a later config that passes --url, --region, and --profile, so the gap is visible in the file. ### A good fit for - Querying an Amazon Managed Prometheus workspace once --url and AWS credentials are set ### Weigh up before choosing - This review did not execute the resource. - install.command is null. The package name is split across JSON args rather than a single shell line. - The basic configuration starts the package with no workspace URL. This review did not start the server, so it does not say whether that config can query anything. - The README and the directory LICENSE both say Apache-2.0. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - src/prometheus-mcp-server/README.md - src/prometheus-mcp-server/LICENSE ### Our findings - The server says it runs instant and range PromQL, lists metrics, and uses AWS SigV4 against Amazon Managed Prometheus. - The basic Kiro JSON args are only awslabs.prometheus-mcp-server@latest. A later example adds --url, --region, and --profile. - The Windows example sets type to stdio. Prerequisites are Python 3.10 or higher, AWS credentials, and a workspace. None of those were used. ### Not established by this review - The resource was not executed and its tools were not called. - No PromQL query was sent. - No workspace URL was configured. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Connect a server deliberately. [Upstream setup instructions ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/README.md) - Install a client config whose command is uvx and whose args start with awslabs.prometheus-mcp-server@latest. - The optional-arguments example adds --url for the workspace endpoint, plus --region and --profile. - The Windows block uses uv tool run and sets type to stdio. No single shell line is recorded as install.command. ### Before you start - Python 3.10 or higher and uv - AWS credentials that can call Amazon Managed Prometheus - A workspace URL ### Compatibility Kiro · Cursor · VS Code ### Implementation python ### Transports stdio ### PromQL through the operator's AWS credentials - List workspaces and metrics - Run instant and range queries - Does not document a write or rule-management tool in the features list ### Cost model Apache-2.0; no AWS API call was made 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - [Prometheus MCP README ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/README.md Supports: SigV4 PromQL scope and the two configs - [Directory LICENSE ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/prometheus-mcp-server/LICENSE Supports: Apache License Version 2.0 KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Apache SkyWalking MCP Server ↗ Queries a SkyWalking OAP you already run. The inspected install builds a local image; it does not pull a published one.](/mcp-servers/apache-skywalking-mcp/)[### Axiom MCP ↗ Queries Axiom telemetry and manages observability resources through an account-authorized hosted connection.](/mcp-servers/axiom/)[### Checkly MCP Server ↗ Checkly's hosted MCP server over Streamable HTTP: inspect check status and results, test sessions, RCA and result assets, trigger deployed checks, manage monitors and groups, environment variables and status-page incidents. OAuth is recommended; user and service API keys are the documented alternatives.](/mcp-servers/checkly/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/) ## Continue your investigation - [Inspect resource evidence](/tools/) - [Choose a host](/agents/) - [Inspect reusable workflows](/skills/) - [Use Undominated data](/api/)