MCP Catalogs
Homemcp-victorialogs screenshot

mcp-victorialogs

by VictoriaMetrics·73·Score 48

VictoriaLogs MCP server provides access to VictoriaLogs observability data through Model Context Protocol.

monitoringdeveloper-toolsops-infra
19
Forks
7
Open issues
this month
Last commit
2d ago
Indexed

Overview

This is a fully functional MCP server that bridges VictoriaLogs with AI models and tools. It implements the Model Context Protocol specification, allowing seamless integration with VictoriaLogs APIs. The server exposes tools for querying logs, exploring data, showing instance parameters, listing streams/fields, and querying statistics. It supports multiple modes including stdio, SSE, and HTTP, with comprehensive configuration options and built-in documentation search capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Debugging system issues by querying logs through AI assistants
you:Automating observability tasks using AI-powered tools
you:Creating custom dashboards with log data through LLM integration
you:What VictoriaLogs APIs are supported?
you:What transport modes are available?

When to choose this

Choose this when you need AI-driven access to VictoriaLogs for log analysis, metrics, and observability without writing custom API clients.

When NOT to choose this

Don't choose this if you need write access to VictoriaLogs or require integration with non-Victoria observability stacks.

Tools this server exposes

7 tools extracted from the README
  • query_logsquery_logs(query: string, start_time?: string, end_time?: string, step?: string) -> object

    Query logs from VictoriaLogs with optional time range and step parameters

  • show_parametersshow_parameters() -> object

    Show parameters of the VictoriaLogs instance

  • list_streamslist_streams() -> object

    List available streams in VictoriaLogs

  • list_fieldslist_fields(stream?: string) -> object

    List available fields in specified stream or all streams

  • list_field_valueslist_field_values(field: string, stream?: string) -> object

    List values for a specific field in a stream

  • query_statsquery_stats(query: string, start_time?: string, end_time?: string) -> object

    Query statistics for logs as metrics

  • search_docssearch_docs(query: string) -> object

    Search embedded VictoriaLogs documentation

Comparable tools

grafana-mcpprometheus-mcplogs-mcp

Installation

Installation

Go

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

Docker

docker run -d --name mcp-victorialogs \
  -e VL_INSTANCE_ENTRYPOINT=https://your-victorialogs-url \
  -e MCP_SERVER_MODE=http \
  -e MCP_LISTEN_ADDR=:8081 \
  -p 8081:8081 \
  ghcr.io/victoriametrics/mcp-victorialogs

Claude Desktop Configuration

{
  "mcpServers": {
    "victorialogs": {
      "command": "mcp-victorialogs",
      "args": ["--env", "VL_INSTANCE_ENTRYPOINT=https://your-victorialogs-url"]
    }
  }
}

FAQ

What VictoriaLogs APIs are supported?
The MCP server supports almost all read-only APIs of VictoriaLogs, including query functions available in the Web UI.
What transport modes are available?
Three modes are supported: stdio (default), SSE (Server-Sent Events), and HTTP (Streamable HTTP).

Compare mcp-victorialogs with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.