MCP server "mcp-victoriametrics" as configured in VictoriaMetrics/mcp-victoriametrics. Runs in Docker (ghcr.io/victoriametrics/mcp-victoriametrics:1.20.2). Needs 7 environment variables to run.
225 9d agoA
tokens not measured
originalApache-2.0
MCP server "mcp-victorialogs" as configured in VictoriaMetrics/mcp-victorialogs. Runs in Docker (ghcr.io/victoriametrics/mcp-victorialogs:1.9.0). Needs 3 environment variables to run.
97 1mo agoA
tokens not measured
originalApache-2.0
Diagnostic tools for VictoriaMetrics. Analyze query execution traces for performance bottlenecks, orchestrate multi-signal investigations across metrics, logs, traces, and alerts, and design stream aggregation rules to reduce cardinality.
Use when investigating issues, debugging problems for applications, or responding to alerts in the Kubernetes cluster using VictoriaMetrics, VictoriaLogs, or VictoriaTraces.
You are a signal-gathering subagent. Your role is to check the current alert state from VictoriaMetrics and AlertManager. Do NOT form hypotheses or propose root causes. Report raw findings only — the orchestrator handles interpretation.
You are the Logs Discovery Agent. Your role is to discover and query VictoriaLogs for a target namespace or service. You run stream field discovery, facets, field names, and sample log queries.
You are a Metrics Discovery Agent. Your role is to discover and query VictoriaMetrics metrics for a given target namespace and/or service. You execute structured discovery steps and report raw findings. You do NOT form hypotheses, interpret root causes, or draw conclusions — that is the orchestrator's responsibility.
You are the Traces Discovery Agent. Your role is to discover and query VictoriaTraces via the Jaeger-compatible API for a target service. You list services, operations, and dependencies, and search traces to surface raw data for the investigation.
Design VictoriaMetrics stream aggregation rules to reduce cardinality, sample frequency, or query load. Use whenever the user wants to apply, plan, or troubleshoot stream aggregation (-streamAggr.config, -remoteWrite.streamAggr.config), asks how to aggregate a high-cardinality metric, mentions downsampling at vmagent…
Analyze VictoriaMetrics time series cardinality to find optimization opportunities — unused metrics, high-cardinality labels, problematic label values, histogram bloat. Produces actionable report with relabeling and stream aggregation recommendations. Use whenever the user mentions cardinality analysis, series…
Find unused and rarely-queried metrics in VictoriaMetrics using the metricnamesstats API, then suggest optimization actions (drop rules, relabel configs). Use this skill when the user wants to find unused metrics, identify wasted storage, optimize metric ingestion, reduce cardinality by dropping unneeded metrics…
Analyze VictoriaMetrics query trace JSON to diagnose slow queries and produce a structured performance report with time breakdown, bottleneck analysis, and optimization recommendations. ALWAYS use this skill when: (1) the user mentions a VictoriaMetrics or VM trace, query trace, or trace JSON, (2) the user provides or…
Query the full VictoriaMetrics observability stack. Run PromQL/MetricsQL metric queries, search logs with LogsQL, discover distributed traces via Jaeger API, and manage AlertManager alerts and silences.
Query VictoriaLogs via curl. Use when searching logs with LogsQL, running log stats queries, discovering log fields/streams, analyzing log hit patterns, or exploring log facets. Triggers on: log queries, LogsQL, log search, log stats, field discovery, stream discovery, log facets, log hits, log field values.
Query VictoriaTraces via curl using the Jaeger-compatible API. Use when discovering traced services and operations, searching traces by service/operation/duration/tags, retrieving traces by ID, or mapping service dependencies. Triggers on: trace queries, span search, trace ID lookup, service discovery, operation…
Configure, operate, and review VictoriaMetrics Anomaly Detection. Profile time series, select and tune models, validate configurations, run bounded detection tasks, and check persisted-state compatibility.
Design, tune, validate, and test VictoriaMetrics vmanomaly configurations for known metrics or LogsQL queries. Use when choosing static alerting versus ML, selecting a vmanomaly model, configuring Temporal Envelope, building deployment YAML, tuning anomaly sensitivity, or creating VMAlert rules. Trigger on anomaly…
Operate VictoriaMetrics Anomaly Detection (vmanomaly) through its HTTP API. Use when checking health, versions, persisted-state compatibility, self-monitoring metrics, available models, model schemas, server queries, time-series characteristics, shared autotune, or asynchronous detection tasks. Also use for generating…
Audit an existing VictoriaMetrics vmanomaly configuration against runtime capabilities and real data. Use when reviewing model-data fit, scheduler cadence, persisted-state compatibility, cold start, excessive detections, missing anomalies, output cardinality, or upgrade readiness. Trigger on vmanomaly config review…
MCP server "mcp-vmanomaly" as configured in VictoriaMetrics/mcp-vmanomaly. Runs in Docker (ghcr.io/victoriametrics/mcp-vmanomaly:0.3.4). Needs 12 environment variables to run.