MCP Server

Kamustatus provides a Model Context Protocol (MCP) server that lets AI assistants interact with your uptime monitoring data.

What is MCP?

MCP is an open protocol that allows AI assistants (such as Claude, Cursor, and others) to use external tools and data sources. The Kamustatus MCP server exposes your monitors, incidents, and status pages as tools that an AI assistant can call.

Setup

Claude Desktop

Add the following to your Claude Desktop MCP config file (~/.claude/claude_desktop_config.json or equivalent):

{
  "mcpServers": {
    "kamustatus": {
      "command": "kamustatus",
      "args": ["mcp"],
      "env": {
        "KAMUPTIME_API_KEY": "km_your_api_key"
      }
    }
  }
}

Claude Code

Add to your Claude Code MCP settings:

{
  "mcpServers": {
    "kamustatus": {
      "command": "kamustatus",
      "args": ["mcp"],
      "env": {
        "KAMUPTIME_API_KEY": "km_your_api_key"
      }
    }
  }
}

Available Tools

Once connected, the AI assistant can use these tools:

Tool	Description
list_monitors	List all monitors in the project
get_monitor	Get details and current status of a monitor
get_monitor_stats	Get uptime and response time stats
list_incidents	List recent incidents
create_incident	Create a new incident
update_incident	Update an incident status
list_status_pages	List status pages
list_alert_history	View recent alert history

Example Interactions

With the MCP server connected, you can ask your AI assistant things like:

• "Are all my monitors up right now?"
• "What was the uptime for my API monitor last week?"
• "Create an incident for the database outage."
• "Show me recent alerts."

The assistant will use the Kamustatus MCP tools to fetch data and take actions on your behalf.

Requirements

The kamustatus CLI must be installed and available in your PATH. See CLI for installation instructions.