humio-mcp
Enables querying Humio/LogScale dashboards and executing search queries via MCP, with multi-cluster support and configurable time ranges.
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 uvorcurl -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:
HUMIO_MCP_CONFIGenvironment variable./config.toml~/.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
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.