SA
SkillAvatars
Back to MCP Tools

byok-observability-mcp

devops-infra MCP Server

MCP server for Grafana, Prometheus, Kafka UI, and Datadog — bring your own credentials (BYOK)

byalimuratkuslu
VerifiedInstall Ready
devops-infradevops-infra
3 views2 stars0 forksv0.5.2MIT
View on GitHubHomepage

Why This Matters

Discovered via list:awesome-mcp-servers-punkpeye and last synced 3mo ago.

VerifiedInstall Ready
Source
list:awesome-mcp-servers-punkpeye
Stars
2
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx -y byok-observability-mcp

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "byok-observability-mcp": {
      "command": "npx",
      "args": [
        "byok-observability-mcp"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

61
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (61)

Client

Configuration

grafana_query_metrics

Run a PromQL expression via a Grafana datasource

prometheus_health

Check connectivity

Toolset

Covers

grafana_list_alerts

List active alerts from Alertmanager (firing/pending)

prometheus_list_metrics

List all available metric names

grafana_health

Check connectivity, version, and database status

grafana_get_alert_rules

List all configured alert rules across all folders

prometheus_metric_metadata

Get help text and type for a specific metric

kafka_consumer_group_lag

Get per-partition lag for a consumer group

logs

Log search and analytics

grafana_list_datasources

List all datasources (name, type, UID)

kafka_broker_health

Broker count and disk usage per broker

GRAFANA_TOKEN

Grafana

Triage

*"Show me the alert rules for the 'Production' folder."*

apm

APM services, traces, service map

PROMETHEUS_USERNAME

Prometheus

prometheus_query_range

Range PromQL query — metric values over time

ddsql

SQL-style metric queries

feature-flags

Feature flag tracking

KAFKA_UI_URL

Kafka UI

REPORT_BACKENDS

Reports

prometheus_query

Instant PromQL query — current value of a metric

kafka_list_consumer_groups

List consumer groups and their state

incidents

Incident management

cases

Case management

PROMETHEUS_PASSWORD

Prometheus

SLACK_WEBHOOK_URL

Reports

Prometheus

v2.x

kafka_describe_topic

Get partition count, replication factor, and config

llm-obs

LLM observability

DD_TOOLSETS

Datadog

Alerts

*"Are there any firing alerts in Grafana right now?"*

grafana_get_dashboard

Get panels and metadata for a dashboard by UID

synthetics

Synthetic test results

GRAFANA_URL

Grafana

KAFKA_UI_PASSWORD

Kafka UI

Backend

Tested version

obs_health_check

**Unified Health Check.** Runs a parallel check on all backends and returns a status table.

grafana_list_dashboards

Search and list dashboards by name or tag

Tool

Description

kafka_list_clusters

List configured Kafka clusters and their status

kafka_list_topics

List topics in a cluster

core

Metrics, dashboards, monitors, infrastructure

alerting

Monitors, downtimes, alerts

security

Cloud security posture

networks

Network performance monitoring

dbm

Database monitoring

software-delivery

CI/CD pipelines

Variable

Backend

GRAFANA_VERIFY_SSL

Grafana

PROMETHEUS_URL

Prometheus

KAFKA_UI_USERNAME

Kafka UI

DD_API_KEY

Datadog

DD_APP_KEY

Datadog

DD_SITE

Datadog

Level

Meaning

Grafana

v9.x, v10.x, v11.x

Datadog

API key + Application key with read scopes

Goal

Try asking Claude...

Health

*"Run a health check on all systems."*

Browse all MCP servers