humio-mcp

humio-mcp

Enables querying Humio/LogScale dashboards and executing search queries via MCP, with multi-cluster support and configurable time ranges.

Category
Visit Server

README

HumioMCP

MCP server for querying Humio/LogScale dashboards and executing search queries.

Built with FastMCP (Python).

Features

  • list_dashboards — List all dashboards in a Humio repo/view, with optional name filtering
  • get_dashboard_queries — Extract all search queries (with time ranges) from a dashboard's widgets
  • execute_search — Run a search query and get results as JSON (default limit: 200 events)
  • Multi-cluster support via TOML config
  • Both relative time (24h, 7d) and ISO 8601 (2024-01-01T00:00:00Z) supported

Quick Start for Others

Option A: One-click VS Code config (recommended)

No clone needed. Add this to your VS Code settings.json or .vscode/mcp.json:

{
  "servers": {
    "humio-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from", "git+https://github.com/weihong-xu-hpe/humio-mcp.git",
        "humio-mcp"
      ],
      "env": {
        "HUMIO_MCP_CONFIG": "${userHome}/.config/humio-mcp/config.toml"
      }
    }
  }
}

Then create the config file at ~/.config/humio-mcp/config.toml:

default_cluster = "us-west-2"

[clusters.us-west-2]
url = "https://your-humio-url.example.com/logs"
token = "your-api-token"

That's it — uvx handles install and updates automatically.

Prerequisite: uv must be installed (brew install uv or curl -LsSf https://astral.sh/uv/install.sh | sh)

Option B: Clone and run locally

git clone https://github.com/weihong-xu-hpe/humio-mcp.git
cd humio-mcp
uv sync

cp config.example.toml config.toml
# Edit config.toml with your cluster URLs and API tokens

VS Code config for local clone:

{
  "servers": {
    "humio-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/HumioMCP", "mcp", "run", "src/humio_mcp/server.py"]
    }
  }
}

Option C: Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "humio-mcp": {
      "command": "uvx",
      "args": [
        "--from", "git+https://github.com/weihong-xu-hpe/humio-mcp.git",
        "humio-mcp"
      ],
      "env": {
        "HUMIO_MCP_CONFIG": "/Users/yourname/.config/humio-mcp/config.toml"
      }
    }
  }
}

Configuration

Edit config.toml (or ~/.config/humio-mcp/config.toml):

default_cluster = "us-west-2"

[clusters.us-west-2]
url = "https://mira-us-west-2.cloudops.ccs.arubathena.com/logs"
token = "your-api-token"

[clusters.eu-central-1]
url = "https://mira-eu-central-1.example.com/logs"
token = "another-token"

Config search order:

  1. HUMIO_MCP_CONFIG environment variable
  2. ./config.toml
  3. ~/.config/humio-mcp/config.toml

Development

# MCP Inspector (interactive debugging)
uv run mcp dev src/humio_mcp/server.py

# Stdio mode
uv run mcp run src/humio_mcp/server.py

Tools

list_dashboards

Param Type Required Description
repo str Yes Repository/view name
cluster str No Cluster name (default from config)
search_filter str No Filter by name substring

get_dashboard_queries

Param Type Required Description
repo str Yes Repository/view name
dashboard_name str Yes Dashboard name
cluster str No Cluster name

execute_search

Param Type Required Description
repo str Yes Repository/view name
query_string str Yes Humio search query
start str No Start time (default: 24h)
end str No End time (default: now)
cluster str No Cluster name

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured