Mcp Victoriametrics

Overview

Mcp Victoriametrics is a Model Context Protocol server that integrates VictoriaMetrics API and documentation into MCP-compatible AI assistants. Any AI assistant using MCP can directly access VictoriaMetrics tools and data, with the model deciding when and how to use them during conversations or agent runs.

The server runs locally via Docker using the image ghcr.io/victoriametrics-community/mcp-victoriametrics:1.18.0. It communicates over stdio and requires three environment variables for setup: VM_INSTANCE_ENTRYPOINT, VM_INSTANCE_TYPE, and VM_INSTANCE_BEARER_TOKEN for API key authentication. The latest release is v1.18.0, distributed under the Apache-2.0 license with source code available at VictoriaMetrics-Community/mcp-victoriametrics on GitHub.

Mcp Victoriametrics is categorized as a Development tool on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this server for VictoriaMetrics-Community, claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "mcp_victoriametrics": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/victoriametrics-community/mcp-victoriametrics:1.18.0"
      ],
      "env": {
        "VM_INSTANCE_ENTRYPOINT": "<vm-instance-entrypoint>",
        "VM_INSTANCE_TYPE": "<vm-instance-type>",
        "VM_INSTANCE_BEARER_TOKEN": "<vm-instance-bearer-token>"
      }
    }
  }
}

Requires VM_INSTANCE_ENTRYPOINT, VM_INSTANCE_TYPE, VM_INSTANCE_BEARER_TOKEN