MCPgee
MCPgee
MCPgeeMCPgee

VictoriaMetrics Integration

v1.120.1•Monitoring & Observability•stable

MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation

aimcpmcp-servermonitoringobservability
Share:
167
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is VictoriaMetrics Integration?

VictoriaMetrics Integration is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for victoriametrics. provides integration with victoriametrics api and documentation

MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP Server for VictoriaMetrics. Provides integration with Vi

Use Cases

Query VictoriaMetrics time-series
Monitoring and observability
RAG documentation
VictoriaMetrics

Maintainer

LicenseApache 2.0
Languagego
Versionv1.120.1
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx mcp-victoriametrics

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use VictoriaMetrics Integration

The VictoriaMetrics MCP Server bridges AI assistants directly to VictoriaMetrics time-series databases, exposing tools for executing PromQL and MetricsQL queries, browsing metrics and labels, inspecting alerting rules, debugging relabeling configs, and searching embedded VictoriaMetrics documentation. It supports both single-node and cluster deployments as well as VictoriaMetrics Cloud, making it suitable for on-call engineers who want to investigate incidents conversationally and for platform teams who want AI-assisted monitoring workflows.

Prerequisites

  • A running VictoriaMetrics instance (single or cluster) or a VictoriaMetrics Cloud account
  • Go 1.21+ if building from source, or Docker for container deployment
  • The instance URL and optionally a bearer token for authentication
  • An MCP client such as Claude Desktop
1

Download the pre-built binary

Download the latest release binary for your platform from the GitHub releases page. Alternatively use Docker or build from source with 'go build'.

latest=$(curl -s https://api.github.com/repos/VictoriaMetrics/mcp-victoriametrics/releases/latest | grep 'tag_name' | cut -d'"' -f4)
wget https://github.com/VictoriaMetrics/mcp-victoriametrics/releases/download/$latest/mcp-victoriametrics_Linux_x86_64.tar.gz
tar axvf mcp-victoriametrics_Linux_x86_64.tar.gz
2

Set required environment variables

Configure the VictoriaMetrics instance endpoint and type. For VictoriaMetrics Cloud use VMC_API_KEY instead of VM_INSTANCE_ENTRYPOINT.

export VM_INSTANCE_ENTRYPOINT=http://your-vm-instance:8428
export VM_INSTANCE_TYPE=single
# Optional bearer token auth:
export VM_INSTANCE_BEARER_TOKEN=your_token
# For VictoriaMetrics Cloud:
export VMC_API_KEY=your_cloud_api_key
3

Run with Docker (alternative)

Use the official Docker image for a containerized deployment with SSE transport mode so it can be reached over the network.

docker run -d --name mcp-victoriametrics \
  -e VM_INSTANCE_ENTRYPOINT=https://play.victoriametrics.com \
  -e VM_INSTANCE_TYPE=cluster \
  -e MCP_SERVER_MODE=sse \
  -e MCP_LISTEN_ADDR=:8080 \
  -p 8080:8080 \
  ghcr.io/victoriametrics/mcp-victoriametrics
4

Configure Claude Desktop to use the server

Register the binary as an MCP server in claude_desktop_config.json using stdio transport mode.

{
  "mcpServers": {
    "victoriametrics": {
      "command": "/path/to/mcp-victoriametrics",
      "args": [],
      "env": {
        "VM_INSTANCE_ENTRYPOINT": "http://your-vm-instance:8428",
        "VM_INSTANCE_TYPE": "single"
      }
    }
  }
}
5

Disable specific tools if needed

Use the MCP_DISABLED_TOOLS environment variable to turn off tools your deployment doesn't need, reducing the exposed surface area.

export MCP_DISABLED_TOOLS=test_rules,downsampling_filters_debug

VictoriaMetrics Integration Examples

Client configuration

Claude Desktop configuration for VictoriaMetrics MCP server pointing to a local single-node instance.

{
  "mcpServers": {
    "victoriametrics": {
      "command": "/usr/local/bin/mcp-victoriametrics",
      "args": [],
      "env": {
        "VM_INSTANCE_ENTRYPOINT": "http://localhost:8428",
        "VM_INSTANCE_TYPE": "single",
        "VM_INSTANCE_BEARER_TOKEN": "optional_bearer_token"
      }
    }
  }
}

Prompts to try

Example prompts to use with the VictoriaMetrics MCP server for monitoring and observability tasks.

- "What metrics are available in my VictoriaMetrics instance?"
- "Run a range query for 'rate(http_requests_total[5m])' over the last hour"
- "Show me all currently firing alerts"
- "Which metrics have the highest cardinality in my TSDB?"
- "Search the VictoriaMetrics documentation for MetricsQL aggregate functions"
- "Explain this query: sum(rate(node_cpu_seconds_total{mode!='idle'}[5m])) by (instance)"
- "Find unused metrics that could be dropped to reduce storage costs"

Troubleshooting VictoriaMetrics Integration

Connection refused when starting the server against a local VictoriaMetrics instance

Verify your VictoriaMetrics instance is running and accessible at the URL set in VM_INSTANCE_ENTRYPOINT. For single-node deployments the default port is 8428. Test with 'curl http://your-vm-instance:8428/health' before starting the MCP server.

Authentication errors when connecting to VictoriaMetrics with bearer token

Ensure VM_INSTANCE_BEARER_TOKEN contains the full token string without extra whitespace. For VictoriaMetrics Cloud, use VMC_API_KEY instead of bearer token — do not set both simultaneously.

Cluster queries return empty results even though data exists

Confirm VM_INSTANCE_TYPE is set to 'cluster' and that VM_INSTANCE_ENTRYPOINT points to the vmselect component URL, not vminsert or vmstorage. The cluster read path uses vmselect on port 8481 by default.

Frequently Asked Questions about VictoriaMetrics Integration

What is VictoriaMetrics Integration?

VictoriaMetrics Integration is a Model Context Protocol (MCP) server that mcp server for victoriametrics. provides integration with victoriametrics api and documentation It connects AI assistants to external tools and data sources through a standardized interface.

How do I install VictoriaMetrics Integration?

Follow the installation instructions on the VictoriaMetrics Integration GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with VictoriaMetrics Integration?

VictoriaMetrics Integration works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is VictoriaMetrics Integration free to use?

Yes, VictoriaMetrics Integration is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

VictoriaMetrics Integration Alternatives — Similar Monitoring & Observability Servers

Looking for alternatives to VictoriaMetrics Integration? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.

Netdata

★ 78.9k

Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.

Kubeshark

★ 11.9k

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

Mission Control

★ 4.9k

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

Grafana

★ 3.0k

This MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.

Sentrux

★ 2.4k

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

OpenInference

★ 986

OpenTelemetry Instrumentation for AI Observability

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Monitoring & ObservabilityBrowse All Servers

Quick Config Preview

{ "mcpServers": { "mcp-victoriametrics": { "command": "npx", "args": ["-y", "mcp-victoriametrics"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use VictoriaMetrics Integration?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides