Ionhour
Let AI agents monitor and manage your infrastructure through the Model Context Protocol. Query, create, and resolve — all in natural language.
@ionhour/mcp-server
Connect AI assistants to your IonHour uptime monitoring workspace using the Model Context Protocol.
Quick Start
# Option 1: Interactive login (recommended)
npx @ionhour/mcp-server login
# Option 2: Set your API key manually
export IONHOUR_API_KEY=ionh_your_key_here
# Run the MCP server
npx @ionhour/mcp-server
Setup with AI Assistants
Claude Code
claude mcp add ionhour -- npx @ionhour/mcp-server
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ionhour": {
"command": "npx",
"args": ["@ionhour/mcp-server"],
"env": {
"IONHOUR_API_KEY": "ionh_your_key_here"
}
}
}
}
Cursor
Add to your .cursor/mcp.json:
{
"mcpServers": {
"ionhour": {
"command": "npx",
"args": ["@ionhour/mcp-server"],
"env": {
"IONHOUR_API_KEY": "ionh_your_key_here"
}
}
}
}
VS Code (Copilot)
Add to your .vscode/mcp.json:
{
"servers": {
"ionhour": {
"command": "npx",
"args": ["@ionhour/mcp-server"],
"env": {
"IONHOUR_API_KEY": "ionh_your_key_here"
}
}
}
}
Getting an API Key
- Go to your IonHour workspace Settings > API Keys
- Create a new key with Read & Write or Read Only permission
- Copy the key (starts with
ionh_)
Available Tools
Workspace
get_workspace- Get workspace detailsget_workspace_summary- Overview of projects, checks, and incidentsget_workspace_reliability- Uptime, incident count, and MTTR metricslist_team_members- List workspace members and rolessend_invitation- Invite users to the workspace
Projects
list_projects/create_project/update_project
Checks (Monitors)
register_check- Create a new monitoring checklist_checks/list_checks_by_status/find_check_by_nameget_check_status- Detailed status with recent signalsget_check_uptime- Uptime percentage with daily bucketspause_check/resume_check
Signals (Heartbeats)
send_heartbeat- Send a success signalsend_failure_signal- Report a failurelist_signals- View signal history
Incidents
list_incidents/search_incidents/get_incidentget_incident_timeline- Incident history for a checkcreate_incident/acknowledge_incident/resolve_incidentadd_incident_note
Deployments
create_deployment- Start a deployment window (auto-pauses checks)end_deployment- End deployment and resume checkslist_deployments
Dependencies
list_dependencies/get_dependency/create_dependencyupdate_dependency_status
Status Pages & Alerts
list_status_pages/create_status_page/update_status_pagecreate_announcementlist_alert_channels/create_alert_channel/update_alert_channellist_escalation_rules/create_escalation_rule/update_escalation_rule
CLI Commands
npx @ionhour/mcp-server [command] [options]
Commands:
(default) Start the MCP server
login Authenticate via browser and store API key
logout Remove stored credentials
whoami Show current authentication status
Options:
--api-key KEY IonHour API key (or set IONHOUR_API_KEY env var)
--base-url URL API base URL (default: https://api.ionhour.com)
--help, -h Show help
login
Opens your browser to authenticate with IonHour, then automatically creates and stores an API key:
npx @ionhour/mcp-server login
Credentials are stored at ~/.config/ionhour/credentials.json (file permissions: 600).
After login, you can run the MCP server without setting IONHOUR_API_KEY.
How It Works
This package runs a local MCP server over stdio that proxies requests to the IonHour API. Your AI assistant communicates with this local server, which forwards tool calls to your IonHour workspace.
AI Assistant <--stdio--> @ionhour/mcp-server <--HTTPS--> IonHour API
Requirements
- Node.js >= 18
- An IonHour account with an API key
License
MIT
相关服务器
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Hangfire MCP
MCP server for managing Hangfire background jobs
pipeyard
Curated MCP connector marketplace for industry verticals — Construction, Finance, Healthcare, and Logistics with full docs, curl examples and sandbox testing.
BerryRAG
A local RAG system with Playwright MCP integration for Claude and OpenAI embeddings, using local storage.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Chronos Protocol
A robust MCP server that eliminates temporal blindness in AI coding agents through intelligent time tracking, persistent memory, and complete session traceability.
PGYER
MCP Server for PGYER platform, supports uploading, querying apps, etc.
MCP Proxy Server
Aggregates multiple MCP resource servers into a single interface.
Unreal-Blender MCP
A unified server to control Blender and Unreal Engine via AI agents.
MCP Playwright Server
Automate web testing and tasks by connecting Claude Desktop with Playwright.
Wirekitty
Let your agents generate wireframes for your next app or feature, make iterations, and build off approved designs.