VictoriaMetrics Observability Stack integrates with AI assistants through MCP servers and agent skills. The integrations allow AI agents and automation tools to query Metrics, Logs, and Traces, analyze telemetry data, and assist engineers with debugging, observability tasks, root cause analysis, anomaly detection, etc.

Support of OpenTelemetry for Metrics, Logs, and Traces makes VictoriaMetrics Observability Stack optimal for AI observability. Any SDK or AI assistant that can emit telemetry signals in OpenTelemetry format can be integrated with VictoriaMetrics.

MCP Servers

MCP (Model Context Protocol) servers expose observability data and operational capabilities to AI assistants in a structured way. This allows AI agents to query telemetry data, analyze system behavior, and assist engineers in troubleshooting and investigation workflows.

VictoriaMetrics MCP Server

VictoriaMetrics MCP Server provides access to VictoriaMetrics instances, seamless integration with VictoriaMetrics APIs and documentation.

It offers a comprehensive interface for monitoring, observability, and debugging tasks related to VictoriaMetrics, enabling advanced automation and interaction capabilities for engineers and tools.

Capabilities include:

• Query metrics and exploring data (even drawing graphs if your client supports it)
• List and exporting available metrics, labels, labels values and entire time series
• Analyze and testing your alerting and recording rules and alerts
• Show parameters of your VictoriaMetrics instances
• Explore cardinality of your data and metrics usage statistics
• Analyze, trace, prettify and explain your queries
• Debug your relabeling rules, downsampling and retention policy configurations
• Integrate with VictoriaMetrics Cloud

On YouTube: How to Use an AI Assistant with Your Monitoring System – VictoriaMetrics MCP Server.

See more details at VictoriaMetrics/mcp-victoriametrics.

VictoriaLogs MCP Server

VictoriaLogs MCP Server provides access to VictoriaLogs instances, integration with VictoriaLogs APIs and documentation.

It provides a comprehensive interface for working with logs and performing observability and debugging tasks related to VictoriaLogs.

Capabilities include:

• Querying logs and exploring logs data
• Showing parameters of your VictoriaLogs instances
• Listing available streams, fields, field values
• Query statistics for the logs as metrics

See more details at VictoriaMetrics/mcp-victorialogs.

VictoriaTraces MCP Server

VictoriaTraces MCP Server provides access to VictoriaTraces instances, integration with VictoriaTraces APIs and documentation.

It enables AI assistants and tools to interact with distributed tracing data for observability and debugging tasks.

Capabilities include:

• Get services and operations (span names)
• Query traces, explore and analyze traces data

See more details at VictoriaMetrics/mcp-victoriatraces.

vmanomaly MCP Server

vmanomaly MCP Server provides seamless integration with vmanomaly REST API and documentation for AI-assisted anomaly detection, model management, and observability insights.

Capabilities include:

• Health Monitoring: Check vmanomaly server health and build information
• Model Management: List, validate, and configure anomaly detection models (like zscore_online, prophet, and more)
• Configuration Generation: Generate complete vmanomaly YAML configurations
• Alert Rule Generation: Generate vmalert alerting rules based on anomaly score metrics to simplify alerting setup
• Documentation Search: Full-text search across embedded vmanomaly documentation with fuzzy matching

See more details at VictoriaMetrics/mcp-vmanomaly.

Agent Skills

Agent skills help AI agents and automation tools understand, operate, and troubleshoot VictoriaMetrics observability components, including metrics, logs, and traces.

These skills provide predefined workflows and capabilities such as:

• Query metrics, logs, traces and alerts
• Query trace analysis
• Multi-signal investigations
• Cardinality optimization
• Unused metric detection

To install the available skills for AI agents, run:

npx skills add VictoriaMetrics/skills

See more details at VictoriaMetrics/skills.

AI observability

VictoriaMetrics Observability Stack is optimal for monitoring AI agents using auto-instrumentation libraries like OpenLLMetry, OpenInference, OpenLIT. Please see more details in AI Agents Observability with OpenTelemetry and the VictoriaMetrics Stack.

AI code assistants like Claude Code, OpenAI Codex, Gemini CLI, Qwen Code, and OpenCode expose internal telemetry that helps to monitor cost usage, analytics, performance, compliance and improves troubleshooting experience. All major AI coding tools support OpenTelemetry and can be easily integrated into VictoriaMetrics Observability Stack. Please see more details in Vibe coding tools observability with VictoriaMetrics Stack and OpenTelemetry .