MCP Server for vmanomaly

The implementation of Model Context Protocol (MCP) server for vmanomaly - VictoriaMetrics Anomaly Detection product.

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

Features

This MCP server enables AI assistants like Claude to interact with vmanomaly for:

• 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

The MCP server contains embedded up-to-date vmanomaly documentation and is able to search it without online access.

The quality of the MCP Server and its responses depends very much on the capabilities of your client and the quality of the model you are using.

Requirements

• vmanomaly instance (version 1.28.3+) with REST API access
• Go 1.24 or higher (if building from source)

Installation

Go

go install github.com/VictoriaMetrics/mcp-vmanomaly/cmd/mcp-vmanomaly@latest

Binaries

Download the latest release from Releases page and put it to your PATH.

Example for Linux x86_64 (other architectures and platforms are also available):

latest=$(curl -s https://api.github.com/repos/VictoriaMetrics/mcp-vmanomaly/releases/latest | grep 'tag_name' | cut -d\" -f4)
wget https://github.com/VictoriaMetrics/mcp-vmanomaly/releases/download/$latest/mcp-vmanomaly_Linux_x86_64.tar.gz
tar axvf mcp-vmanomaly_Linux_x86_64.tar.gz

Docker

You can run vmanomaly MCP Server using Docker.

This is the easiest way to get started without needing to install Go or build from source.

docker run -d --name mcp-vmanomaly \
  -e VMANOMALY_ENDPOINT=http://localhost:8490 \
  -e MCP_SERVER_MODE=http \
  -e MCP_LISTEN_ADDR=:8080 \
  -p 8080:8080 \
  ghcr.io/victoriametrics/mcp-vmanomaly

You should replace environment variables with your own parameters.

Note that the MCP_SERVER_MODE=http flag is used to enable Streamable HTTP mode. More details about server modes can be found in the Configuration section.

See available docker images in github registry.

Also see Using Docker instead of binary section for more details about using Docker with MCP server with clients in stdio mode.

Source Code

For building binary from source code you can use the following approach:

• Clone repo:

  git clone https://github.com/VictoriaMetrics/mcp-vmanomaly.git
  cd mcp-vmanomaly
  

• Build binary from cloned source code:

  make build
  # after that you can find binary mcp-vmanomaly and copy this file to your PATH or run inplace
  

• Build image from cloned source code:

  docker build -t mcp-vmanomaly .
  # after that you can use docker image mcp-vmanomaly for running or pushing
  

Configuration

MCP Server for vmanomaly is configured via environment variables:

Variable	Description	Required	Default	Allowed values
VMANOMALY_ENDPOINT	vmanomaly server endpoint URL (e.g., http://localhost:8490)	Yes	-	-
VMANOMALY_BEARER_TOKEN	Bearer token for authenticating with vmanomaly API	No	-	-
VMANOMALY_HEADERS	Custom HTTP headers for requests (comma-separated key=value pairs, e.g., X-Custom=value1,X-Auth=value2)	No	-	-
MCP_SERVER_MODE	Server operation mode. See Modes for details.	No	stdio	stdio, http, sse
MCP_LISTEN_ADDR	Address for HTTP server to listen on	No	localhost:8080	-
MCP_DISABLED_TOOLS	Comma-separated list of tools to disable	No	-	-
MCP_DISABLE_RESOURCES	Disable all resources (documentation search will continue to work)	No	false	false, true
MCP_HEARTBEAT_INTERVAL	Heartbeat interval for streamable-http protocol (keeps connection alive through network infrastructure)	No	30s	-
MCP_LOG_LEVEL	Log level: debug (verbose), info (default), warn, or error	No	info	-
MCP_LOG_FILE	Log file path (empty = stderr)	No	stderr	-

Modes

MCP Server supports the following modes of operation (transports):

• stdio - Standard input/output mode, where the server reads commands from standard input and writes responses to standard output. This is the default mode and is suitable for local servers.
• http - Streamable HTTP. Server will expose the /mcp endpoint for HTTP connections.
• sse - Server-Sent Events. Server will expose the /sse and /message endpoints for SSE connections.

[!NOTE] The sse transport mode was officialy deprecated from MCP Specification (version 2025-03-26) and was replaced by Streamable HTTP transport (http mode). In future releases its support can be deprecated, use Streamable HTTP transport if your client supports it.

More info about transports you can find in MCP docs:

• Core concepts → Transports
• Specifications → Transports

Configuration examples

# Basic configuration
export VMANOMALY_ENDPOINT="http://localhost:8490"

# With authentication
export VMANOMALY_ENDPOINT="http://localhost:8490"
export VMANOMALY_BEARER_TOKEN="your-token"

# With custom headers (e.g., behind a reverse proxy)
export VMANOMALY_HEADERS="X-Custom-Header=value1,X-Another=value2"

# Server mode
export MCP_SERVER_MODE="http"
export MCP_LISTEN_ADDR="0.0.0.0:8080"

# Logging
export MCP_LOG_LEVEL="debug"
export MCP_LOG_FILE="/tmp/mcp-vmanomaly.log"

Endpoints

In HTTP and SSE modes the MCP server provides the following endpoints:

Endpoint	Description
/mcp	HTTP endpoint for streaming messages in HTTP mode (for MCP clients that support Streamable HTTP)
/metrics	Metrics in Prometheus format for monitoring the MCP server
/health/liveness	Liveness check endpoint to ensure the server is running
/health/readiness	Readiness check endpoint to ensure the server is ready to accept requests
/sse + /message	Endpoints for messages in SSE mode (for MCP clients that support SSE)

Setup in clients

Cursor

Go to: Settings → Cursor Settings → MCP → Add new global MCP server and paste the following configuration into your Cursor ~/.cursor/mcp.json file:

{
  "mcpServers": {
    "vmanomaly": {
      "command": "/path/to/mcp-vmanomaly",
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

See Cursor MCP docs for more info.

Claude Desktop

Add this to your Claude Desktop claude_desktop_config.json file (you can find it if open Settings → Developer → Edit config):

{
  "mcpServers": {
    "vmanomaly": {
      "command": "/path/to/mcp-vmanomaly",
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

See Claude Desktop MCP docs for more info.

Claude Code

Run the command:

claude mcp add vmanomaly -- /path/to/mcp-vmanomaly \
  -e VMANOMALY_ENDPOINT=http://localhost:8490 \
  -e VMANOMALY_BEARER_TOKEN=<YOUR_TOKEN> \
  -e VMANOMALY_HEADERS="X-Custom=value1,X-Auth=value2"

See Claude Code MCP docs for more info.

Visual Studio Code

Add this to your VS Code MCP config file:

{
  "servers": {
    "vmanomaly": {
      "type": "stdio",
      "command": "/path/to/mcp-vmanomaly",
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

See VS Code MCP docs for more info.

Zed

Add the following to your Zed config file:

  "context_servers": {
    "vmanomaly": {
      "command": {
        "path": "/path/to/mcp-vmanomaly",
        "args": [],
        "env": {
          "VMANOMALY_ENDPOINT": "http://localhost:8490",
          "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
          "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
        }
      },
      "settings": {}
    }
  }

See Zed MCP docs for more info.

JetBrains IDEs

• Open Settings → Tools → AI Assistant → Model Context Protocol (MCP).
• Click Add (+)
• Select As JSON
• Put the following to the input field:

{
  "mcpServers": {
    "vmanomaly": {
      "command": "/path/to/mcp-vmanomaly",
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

Windsurf

Add the following to your Windsurf MCP config file:

{
  "mcpServers": {
    "vmanomaly": {
      "command": "/path/to/mcp-vmanomaly",
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

See Windsurf MCP docs for more info.

Using Docker instead of binary

You can run vmanomaly MCP server using Docker instead of local binary.

You should replace run command in configuration examples above in the following way:

{
  "mcpServers": {
    "vmanomaly": {
      "command": "docker",
      "args": [
        "run",
        "-i", "--rm",
        "-e", "VMANOMALY_ENDPOINT",
        "-e", "VMANOMALY_BEARER_TOKEN",
        "-e", "VMANOMALY_HEADERS",
        "ghcr.io/victoriametrics/mcp-vmanomaly"
      ],
      "env": {
        "VMANOMALY_ENDPOINT": "http://localhost:8490",
        "VMANOMALY_BEARER_TOKEN": "<YOUR_TOKEN>",
        "VMANOMALY_HEADERS": "X-Custom=value1,X-Auth=value2"
      }
    }
  }
}

Usage

After installing and configuring the MCP server, you can start using it with your favorite MCP client.

You can start dialog with AI assistant from the phrase:

Use MCP vmanomaly in the following answers

But it's not required, you can just start asking questions and the assistant will automatically use the tools and documentation to provide you with the best answers.

Toolset

MCP vmanomaly provides tools organized into categories:

Health & Info (3 tools)

Tool	Description
vmanomaly_health_check	Check vmanomaly server health status
vmanomaly_get_buildinfo	Get build information (version, build time, Go version)
vmanomaly_get_metrics	Get vmanomaly server metrics in Prometheus format

Model Configuration (3 tools)

Tool	Description
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 model configuration before using it

Configuration (1 tool)

Tool	Description
vmanomaly_validate_config	Validate complete vmanomaly YAML configuration

Documentation (1 tool)

Tool	Description
vmanomaly_search_docs	Full-text search across vmanomaly documentation with fuzzy matching

Compatibility (1 tool)

Tool	Description
vmanomaly_check_compatibility	Check if persisted state is compatible with runtime version

Alerting (1 tool)

Tool	Description
vmanomaly_generate_alert_rule	Generate VMAlert rule YAML for anomaly score alerting

Dialog example

This is an example dialog showing how AI assistant can help with vmanomaly configuration and anomaly detection:

• You: I want to set up anomaly detection for CPU usage. What models are available?

• Assistant: I can help you set up anomaly detection for CPU usage. Let me check available models in vmanomaly.

  Your vmanomaly instance supports the following anomaly detection models:

  • zscore - Statistical model based on z-score (standard deviations from mean)
  • prophet - Facebook's Prophet model for time series with seasonality
  • mad - Median Absolute Deviation model
  • holtwinters - Holt-Winters seasonal method
  • isolation_forest_univariate - Isolation Forest for univariate time series
  • rolling_quantile - Rolling quantile-based detection
  • auto - Automatic model selection

  For CPU usage monitoring, I'd recommend starting with zscore model as it's simple, fast, and works well for metrics with stable patterns. Would you like me to generate a configuration?

• You: Yes, please generate a configuration for monitoring CPU usage with zscore model

• Assistant: I'll generate a complete vmanomaly configuration for CPU usage monitoring with the zscore model:

  scheduler:
    infer_every: "1m"
    fit_every: "1h"
    fit_window: "2d"
  
  reader:
    datasource_url: "http://victoriametrics:8428"
    queries:
      cpu_usage: "avg(rate(node_cpu_seconds_total{mode!='idle'}[5m])) by (instance)"
    step: "1m"
  
  models:
    zscore_cpu:
      class: "zscore"
      z_threshold: 2.5
  
  writer:
    datasource_url: "http://victoriametrics:8428"
  

  This configuration will:

  • Run inference every minute
  • Retrain the model every hour using the last 2 days of data
  • Use z-score model with threshold of 2.5 standard deviations
  • Monitor CPU usage across all instances

  Would you like me to validate this configuration or adjust any parameters?

• You: Looks good! Can you create a detection task to test it?

• Assistant: I'll create an anomaly detection task to test the configuration on your recent CPU data:

  Task created successfully! Here's the status:

  • Task ID: task-abc-123
  • Status: Running
  • Model: zscore with z_threshold=2.5
  • Time range: Last 24 hours
  • Progress: Processing data...

  The task is analyzing your CPU usage data. You can check the results in VictoriaMetrics by querying the anomaly score metrics. Would you like me to check the task status or show you how to query the results?

During this dialog, the assistant used the following tools:

• vmanomaly_list_models to get available model types
• vmanomaly_validate_config to validate the configuration
• vmanomaly_create_detection_task to start anomaly detection
• vmanomaly_search_docs to provide context about model parameters

Monitoring

In HTTP and SSE modes the MCP Server provides metrics in Prometheus format at the /metrics endpoint.

Tracked operations:

• mcp_vmanomaly_initialize_total - Client connections
• mcp_vmanomaly_call_tool_total{name,is_error} - Tool calls with success/error tracking
• mcp_vmanomaly_read_resource_total{uri} - Documentation resource reads
• mcp_vmanomaly_list_*_total - List operations (tools, resources, prompts)
• mcp_vmanomaly_error_total{method,error} - Errors by method and type

Example:

# Start in HTTP mode
VMANOMALY_ENDPOINT="http://localhost:8490" MCP_SERVER_MODE=http ./bin/mcp-vmanomaly

# Query metrics
curl http://localhost:8080/metrics

Roadmap

• Add prompts for common vmanomaly workflows (model selection, troubleshooting)
• Grafana dashboard for MCP server monitoring
• Add API compatibility matrix to gracefully handle version differences between MCP client and vmanomaly server (API is evolving, features may be unavailable)

Disclaimer

AI services and agents along with MCP servers like this cannot guarantee the accuracy, completeness and reliability of results. You should double check the results obtained with AI.

The quality of the MCP Server and its responses depends very much on the capabilities of your client and the quality of the model you are using.

Contributing

Contributions to the MCP vmanomaly project are welcome!

Please feel free to submit issues, feature requests, or pull requests.

Related Projects

• vmanomaly - VictoriaMetrics anomaly detection
• VictoriaMetrics - Time series database
• mcp-victoriametrics - MCP server for VictoriaMetrics
• Model Context Protocol - MCP specification

Support

For vmanomaly-specific questions, see the vmanomaly documentation.

For MCP server issues, please open an issue in this repository.