MCP Server

Manage your monitoring from your editor.

Larm has a built-in MCP server. Check uptime, create monitors, manage incidents, and set up alerts — all through natural language from your AI coding tool. Available on all plans, including free.

Setup

Connect in 30 seconds.

Claude Code

claude mcp add larm --transport http https://app.larm.dev/mcp

Or add to your project's .mcp.json:

{
  "mcpServers": {
    "larm": {
      "type": "http",
      "url": "https://app.larm.dev/mcp"
    }
  }
}

Claude Desktop

Open Settings > Developer > Edit Config and add:

{
  "mcpServers": {
    "larm": {
      "type": "http",
      "url": "https://app.larm.dev/mcp"
    }
  }
}

Cursor

Open Settings > MCP Servers, or add to .cursor/mcp.json:

{
  "mcpServers": {
    "larm": {
      "type": "http",
      "url": "https://app.larm.dev/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json:

{
  "servers": {
    "larm": {
      "type": "http",
      "url": "https://app.larm.dev/mcp"
    }
  }
}

Note: VS Code uses "servers" as the root key, not "mcpServers".

The first time you use a Larm tool, your editor opens a browser window. Log in, approve access, and you're connected. Tokens refresh automatically.

Tools

12 tools. Read and write.

Read

list_monitors

List all monitors with their current state

get_monitor

Full details: config, state, uptime %, p95, error rate

get_uptime_summary

Fleet-wide uptime, incident count, and MTTR

list_alert_channels

All configured alert channels

list_state_transitions

Monitor state changes in the last 24 hours

Write

create_monitor

Create a new HTTP monitor

update_monitor

Change URL, interval, timeout, or enable/disable

create_alert_channel

Create a webhook, email, Discord, or other channel

test_alert_channel

Send a test notification

list_incidents

List status page incidents

create_incident

Create an incident, optionally publish to a status page

update_incident

Post updates, advance status, or resolve

Examples

Just ask.

"What's the uptime of my monitors this week?"

"Create a monitor for https://api.example.com/health"

"Set up a Discord webhook for alerts"

"Create an incident — the database is down — and publish it to the production status page"

"Resolve the database incident with a message that the fix is deployed"

"Pause the staging monitor"

Start monitoring in minutes.

Free plan. No credit card required. MCP access included.