MCP vmanomaly Server

This MCP server enables intelligent assistants to interact with the vmanomaly anomaly detection system via a standardized Model Context Protocol interface. It provides health checks, model management, configuration generation, alert rule generation, and documentation search, all with embedded up-to-date vmanomaly documentation for offline use. Use it to integrate AI-assisted workflows with your vmanomaly deployment and observability tooling.

How to use

You will run the MCP server alongside your vmanomaly instance and connect your MCP client to either the HTTP or the standard I/O transport. Use the HTTP transport to expose a streaming endpoint that your client can connect to over the network. Use the stdio transport when you want to run the MCP server as a local process and interact via standard input and output.

How to install

Prerequisites you need before installation: a running vmanomaly instance (version 1.28.3+ with REST API access) and a Go toolchain if you plan to build from source.

Installation options are shown here. Choose the path that matches your environment.

Additional sections

Configuration details, security considerations, usage examples, and troubleshooting tips are provided below to help you deploy and operate the MCP server effectively.

Available tools

vmanomaly_health_check

Check vmanomaly server health status

vmanomaly_get_buildinfo

Get build information including version and Go version

vmanomaly_get_metrics

Retrieve vmanomaly metrics in Prometheus format

vmanomaly_list_models

List all available anomaly detection model types

vmanomaly_get_model_schema

Get JSON schema for a specific model type

vmanomaly_validate_model_config

Validate a model configuration before use

vmanomaly_validate_config

Validate complete vmanomaly YAML configuration

vmanomaly_search_docs

Full-text search across vmanomaly documentation with fuzzy matching

vmanomaly_check_compatibility

Check if persisted state is compatible with runtime version

vmanomaly_generate_alert_rule

Generate VMAlert rule YAML for anomaly score alerting