VictoriaLogs MCP Server

The implementation of Model Context Protocol (MCP) server for VictoriaLogs.

This provides access to your VictoriaLogs instance and seamless integration with VictoriaLogs APIs and documentation. It can give you a comprehensive interface for logs, observability, and debugging tasks related to your VictoriaLogs instances, enable advanced automation and interaction capabilities for engineers and tools.

Features

This MCP server allows you to use almost all read-only APIs of VictoriaLogs, i.e. all functions available in Web UI:

• Querying logs and exploring logs data
• Showing parameters of your VictoriaLogs instance
• Listing available streams, fields, field values
• Query statistics for the logs as metrics
• UI with setup instructions and tools inspection on the root endpoint (only in Streamable HTTP mode)

In addition, the MCP server contains embedded up-to-date documentation and is able to search it without online access.

More details about the exact available tools and prompts can be found in the Usage section.

You can combine functionality of tools, docs search in your prompts and invent great usage scenarios for your VictoriaLogs instance. And please note the fact that 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.

You can also combine the MCP server with other observability or doc search related MCP Servers and get even more powerful results.

Try without installation

There is a publicly available instance of the VictoriaMetrics MCP Server that you can use to test the features without installing it:

https://play-vmlogs-mcp.victoriametrics.com/mcp

Attention! This URL is not supposed to be opened in a browser, it is intended to be used in MCP clients.

It's available in Streamable HTTP Mode mode and configured to work with Public VictoriaLogs Playground.

Here is example of configuration for Claude Desktop:

Requirements

• VictoriaLogs instance: (single-node or cluster)
• Go 1.26 or higher (if you want to build from source)

Installation

Go

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

Binaries

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

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

latest=$(curl -s https://api.github.com/repos/VictoriaMetrics/mcp-victorialogs/releases/latest | grep 'tag_name' | cut -d\" -f4)
wget https://github.com/VictoriaMetrics/mcp-victorialogs/releases/download/$latest/mcp-victorialogs_Linux_x86_64.tar.gz
tar axvf mcp-victorialogs_Linux_x86_64.tar.gz

Docker

You can run VictoriaLogs 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-victorialogs \
  -e VL_INSTANCE_ENTRYPOINT=https://play-vmlogs.victoriametrics.com \
  -e MCP_SERVER_MODE=http \
  -e MCP_LISTEN_ADDR=:8081 \
  -p 8081:8081 \
  ghcr.io/victoriametrics/mcp-victorialogs

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:

  bash

  Copy

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

• Build binary from cloned source code:

  bash

  Copy

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

• Build image from cloned source code:

  Terminal

  Copy

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

Helm

Check out VictoriaLogs MCP Server Helm chart documentation for more details about installation using Helm.

Configuration

MCP Server for VictoriaLogs is configured via environment variables:

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.
• sse - Server-Sent Events. Server will expose the /sse and /message endpoints for SSE connections.
• http - Streamable HTTP. Server will expose the /mcp endpoint for HTTP connections.

More info about transports you can find in MCP docs:

• Core concepts -> Transports
• Specifications -> Transports

Сonfiguration examples

# For a public playground
export VL_INSTANCE_ENTRYPOINT="https://play-vmlogs.victoriametrics.com"

# Custom headers for authentication (e.g., behind a reverse proxy)
# Expected syntax is key=value separated by commas
export VL_INSTANCE_HEADERS="<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"

# Forward specific headers from incoming MCP requests to VictoriaLogs
export MCP_PASSTHROUGH_HEADERS="X-Token,X-Access-Key"

# Server mode
export MCP_SERVER_MODE="sse"
export MCP_SSE_ADDR="0.0.0.0:8081"
export MCP_DISABLED_TOOLS="hits,facets"

Endpoints

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

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": {
    "victorialogs": {
      "command": "/path/to/mcp-victorialogs",
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

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": {
    "victorialogs": {
      "command": "/path/to/mcp-victorialogs",
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

See Claude Desktop MCP docs for more info.

Claude Code

Run the command:

claude mcp add victorialogs -- /path/to/mcp-victorialogs \
  -e VL_INSTANCE_ENTRYPOINT=<YOUR_VL_INSTANCE> \
  -e VL_INSTANCE_BEARER_TOKEN=<YOUR_VL_BEARER_TOKEN> \
  -e VL_INSTANCE_HEADERS="<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"

See Claude Code MCP docs for more info.

Codex

Codex CLI and the IDE extension use the same MCP configuration file: ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Run the command:

codex mcp add victorialogs \
  --env VL_INSTANCE_ENTRYPOINT=<YOUR_VL_INSTANCE> \
  --env VL_INSTANCE_BEARER_TOKEN=<YOUR_VL_BEARER_TOKEN> \
  --env VL_INSTANCE_HEADERS="<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>" \
  -- /path/to/mcp-victorialogs

Or add the following to your Codex ~/.codex/config.toml file:

[mcp_servers.victorialogs]
command = "/path/to/mcp-victorialogs"

[mcp_servers.victorialogs.env]
VL_INSTANCE_ENTRYPOINT = "<YOUR_VL_INSTANCE>"
VL_INSTANCE_BEARER_TOKEN = "<YOUR_VL_BEARER_TOKEN>"
VL_INSTANCE_HEADERS = "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"

If you run the server in Streamable HTTP mode, you can register it with:

codex mcp add victorialogs --url http://localhost:8081/mcp

See Codex MCP docs for more info.

Visual Studio Code

Add this to your VS Code MCP config file:

{
  "servers": {
    "victorialogs": {
      "type": "stdio",
      "command": "/path/to/mcp-victorialogs",
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

See VS Code MCP docs for more info.

Zed

Add the following to your Zed config file:

  "context_servers": {
    "victorialogs": {
      "command": {
        "path": "/path/to/mcp-victorialogs",
        "args": [],
        "env": {
                  "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
      },
      "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": {
    "victorialogs": {
      "command": "/path/to/mcp-victorialogs",
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

Windsurf

Add the following to your Windsurf MCP config file.

{
  "mcpServers": {
    "victorialogs": {
      "command": "/path/to/mcp-victorialogs",
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

See Windsurf MCP docs for more info.

Using Docker instead of binary

You can run VictoriaLogs MCP Server using Docker instead of local binary.

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

{
  "mcpServers": {
    "victorialogs": {
      "command": "docker",
        "args": [
          "run",
          "-i", "--rm",
          "-e", "VL_INSTANCE_ENTRYPOINT",
          "-e", "VL_INSTANCE_BEARER_TOKEN",
          "-e", "VL_INSTANCE_HEADERS",
          "ghcr.io/victoriametrics/mcp-victorialogs",
        ],
      "env": {
        "VL_INSTANCE_ENTRYPOINT": "<YOUR_VL_INSTANCE>",
        "VL_INSTANCE_BEARER_TOKEN": "<YOUR_VL_BEARER_TOKEN>",
        "VL_INSTANCE_HEADERS": "<HEADER>=<HEADER_VALUE>,<HEADER>=<HEADER_VALUE>"
      }
    }
  }
}

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 VictoriaLogs 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 VictoriaLogs provides numerous tools for interacting with your VictoriaLogs instance.

Here's a list of available tools:

Prompts

The server includes pre-defined prompts for common tasks.

These are just examples at the moment, the prompt library will be added to in the future:

FAQ

Why is the MCP server using more resources than I would expect from a simple API proxy?

The server contains an embedded vector database with VictoriaMetrics documentation and blog posts for the documentation tool. It helps to answer complex questions about VictoriaLogs without providing all data to LLM.
This is the main source of resource usage. To reduce it, add documentation to MCP_DISABLED_TOOLS environment variable to completely disable the vector database loading.

How to use one MCP server instance for several VictoriaMetrics instances?

You can use MCP_PASSTHROUGH_HEADERS parameter in the MCP Server together with Header-based routing in vmauth to route MCP calls between instances based on HTTP header values from your MCP client config.

Roadmap

• Support "Explain query" tool
• Support optional integration with VictoriaMetrics Cloud
• Add some extra knowledge to server in addition to current documentation tool:
  • VictoriaMetrics blog posts
  • Github issues
  • Public slack chat history
  • CRD schemas
• Implement multitenant version of MCP (that will support several deployments)
• Add flags/configs validation tool
• Enabling/disabling tools via configuration

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 VictoriaLogs project are welcome!

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