VictoriaMetrics is a fast, cost-effective and scalable time-series database and monitoring solution, designed for collecting and analyzing metrics data in distributed systems.
Enables agents to connect through a single gateway that has a decision model pick which MCP tools and playbooks are relevant to each request, so the LLM only sees the few schemas it needs, and to then invoke those tools on the underlying servers. This cuts tool-selection cost and prompt size dramatically when many MCP servers are connected.
2
4
MIT
Why this server?
Provides tools for investigating service incidents across the VictoriaMetrics observability stack (VictoriaMetrics for metrics via MetricsQL, VictoriaLogs and VictoriaTraces for logs and traces via LogsQL). Enables an agent to ask what changed in a time window and get back a short, ranked digest of changes across metrics, logs and traces — including request/error rates, latency, CPU, memory, consumer lag, new or spiking error-log patterns, and per-span errors — with cause-vs-echo attribution that identifies the service where a failure started and labels affected callers as echoes.
Enables AI agents to ask what changed in a time window and get back a short, ranked answer across metrics, logs and traces, with the service where a failure started identified and its echoes in other services labelled as such. Read-only and deterministic, it scores changes against a baseline and trims results to a token budget, so agents avoid paging through raw queries and blaming the loudest symptom.
4
Apache 2.0
Why this server?
Provides tools for reading and writing time series data to VictoriaMetrics, including capabilities for querying data over specific time ranges, importing Prometheus format data, and retrieving label information.
Radar is an open-source Kubernetes observability and diagnostics MCP server. It exposes cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions to AI agents through the Model Context Protocol.
25
358 npm
4,009
Apache 2.0
Why this server?
Planned direct integration as a Prometheus-compatible backend, allowing the same bounded metrics query and evidence contract as Prometheus without requiring Grafana.
Enables AI assistants to manage Docker containers and Compose stacks through natural language, including lifecycle operations, logs, stats, and secure remote access.
21
8 npm
3
MIT
Why this server?
Provides read-only tools for querying and investigating VictoriaLogs (VictoriaMetrics' log database) over its LogsQL query API. Capabilities include searching logs by query with pagination, looking up logs by exact ID or stream ID, discovering streams, field names and field values, computing hit/trend histograms over time buckets, and running arbitrary aggregation queries such as stats grouped by field.
A read-only MCP server that lets AI clients investigate logs stored in VictoriaLogs over stdio, offering LogsQL search, UUID/stream lookups, stream and field discovery, hit aggregation, and stats queries with time-range and filtering controls. It supports bearer, basic, or anonymous auth, multi-tenant account/project IDs, and response size and timeout limits.
8
17 npm
MIT
Why this server?
Integrates with VictoriaMetrics vmanomaly for health monitoring, model management, configuration generation, alert rule generation, and documentation search.
MCP server that integrates with VictoriaMetrics vmanomaly API to enable AI-assisted anomaly detection, model management, and configuration generation.
11
Apache 2.0
Why this server?
Allows querying pipeline metrics and custom PromQL queries against VictoriaMetrics, enabling monitoring of throughput, latency, dead-letter queue rate, and other operational metrics.
Model Context Protocol server for managing and diagnosing GlassFlow streaming pipelines, exposing pipeline CRUD, metrics queries, log search, and a composite diagnostic tool as MCP tools that AI agents can call over SSE transport.
