Reported issues for Prometheus MCP Server

Pod holds 11 of 11 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Prometheus MCP Server.

Most discussed

Add truncation and filtering support for tools with large responses (e.g., list_rules, list_alerts, list_targets)

I'm experiencing context overflow when calling list_rules because standard Kubernetes rule templates contain a very large number of elements. The response size exceeds the LLM's context window capacity.

Examples of large outputs:

• list_rules — K8s standard rule templates with many alerting and recording rules
• list_alerts — Large environments with numerous active alerts
• list_targets — Many scrape targets across multiple namespaces
• tsdb_stats — TSDB statistics can be substant

Read the thread · 2026-04-02 · open · external user · 6 comments

Can Not Load MCP Resource

Hello,

I’m unable to successfully load a resource. I’m using Cherry Studio with the Claude model. The MCP tool itself works fine, but the MCP resource cannot be loaded correctly or accessed.

I’ve attached screenshots of my configuration and prompt. Could you please take a look and let me know if I’m doing something wrong?

Authn, authz, HTTPS, Rate limiting, other http access controls to HTTP/SSE server

Currently, the MCP server supports using a prometheus HTTP config file to configure access for the MCP server to connect with the backend prometheus api. However, there are no options to configure security access to the MCP server itself. This is especially important when running in SSE/HTTP transport modes, as it can mean the MCP server is running in a shared/multi-tenant environment, with concurrent users.

Read the thread · 2025-08-11 · closed · outside contributor · 4 comments

SSE/HTTP transport: enable keepalive/heartbeat to prevent idle connection drops

When running the MCP server in HTTP transport mode (e.g., in a Podman container), the SSE connection reliably drops after a few minutes of idle time. After disconnection, all MCP tool calls fail until the client reconnects. This makes automated workflows (e.g., claude -p with a prompt) unreliable since the connection dies between runs.

This is a well-known issue across MCP servers using SSE transport.

Claude's suggestion

The mcp-go SDK already provides the solution: WithKeepAlive / WithKe

Read the thread · 2026-03-04 · closed · 3 comments

Support Multiple Prometheus Data Sources in a Single MCP Server Instance

We would like to request support for multiple Prometheus data sources within a single instance of the Prometheus MCP Server.

In our environment, we have hundreds of Prometheus instances (e.g., one per cluster or tenant), but we prefer to deploy only one MCP server for operational simplicity and resource efficiency. Currently, the MCP server appears to be configured for a single fixed Prometheus endpoint.

It would be extremely valuable if the MCP server could: Accept a list of named Prometheus

Read the thread · 2025-12-13 · open · external user · 3 comments

Consider supporting 3rd party Prometheus HTTP API implementations via flag (ex: --backend=thanos)

About

Prometheus is often a component within a larger collection of systems to store/manage/query metrics. As such, some 3rd party systems implement at least part of the Prometheus HTTP API. This is especially true for API endpoints like: query, range query, exemplar query, label names, label values, series, metric metadata, etc so that these 3rd party systems can serve as a "drop in" replacement for use with querying metrics in systems like grafana/perses.

Proposal

Add a flag `--backen

Read the thread · 2025-07-26 · closed · outside contributor · 3 comments

Failed to validate tool mcp_prometheusmcp_delete_series

docker run --rm -p 8080:8080 ghcr.io/tjhop/prometheus-mcp-server:latest --prometheus.url "http://localhost:9090/" --mcp.transport "http" --web.listen-address ":8080"

When I try to run MCP server and access it via vscode client, i am seeing below error

What metrics are available?

Failed to validate tool mcp_prometheusmcp_delete_series: Error: tool parameters array type must have items. Please open a Github issue for the MCP server or extension which provides this tool

Op

2025-10-29 11:15:49.

Read the thread · 2025-10-29 · open · external user · 2 comments

Tools with EmptyInput missing 'properties' field in JSON Schema (OpenAI API incompatibility)

Problem

Tools that use EmptyInput (empty struct with no fields) generate JSON Schemas without a properties field:

{"type":"object","additionalProperties":false}

The OpenAI API requires all object schemas to include a properties field, even when empty. This causes errors like:

Invalid schema for function 'prometheus__alertmanagers': In context=(), object schema missing properties.

This affects 17 tools: alertmanagers, flags, list_alerts, tsdb_stats, `

Read the thread · 2026-04-08 · closed · external user · 1 comment

Most recent

Create example grafana dashboard

Title

Read the thread · 2025-10-18 · closed · outside contributor · 1 comment

Consider adding a version gate to tools/api calls

I noticed the recent addition of the TSDB blocks endpoint in the prometheus HTTP api docs and was preparing to add support for it within the server. I tried quickly against the prometheus instance on my laptop and got a 404 because my laptop is still running prometheus v3.5.0.

To keep the MCP server api-complete, support will be added for the endpoint. But since the endpoint is so new, interactions with tools/api calls w

Read the thread · 2025-10-18 · closed · outside contributor · 0 comments

Go install fails due to embedding docs submodule contents

As far as I know, go install cannot handle Git submodules correctly. Consequently, go install github.com/tjhop/prometheus-mcp-server/cmd/prometheus-mcp-server@latest (v0.6.0) fails with an error:

go/pkg/mod/github.com/tjhop/prometheus-mcp-server@v0.6.0/cmd/prometheus-mcp-server/main.go:40:13: pattern external/docs/docs: no matching files found

This is due to embedding the Prometheus docs submodule here: https://github.com/tjhop/prometheus-mcp-server/blob/26794ec55411449a23a6e0e2fd0

Read the thread · 2025-09-25 · closed · external user · 0 comments

The remaining reports are on the project's issue tracker.