−50%

50% off your first month on any paid plan · code WELCOME50 · until Nov 30

Start free →

MCP Server

MCP Server

The WatchCron MCP server lets AI assistants manage your monitors through natural language. It implements the Model Context Protocol (MCP) — an open standard that connects AI agents to external tools. Instead of writing API calls, your AI assistant can create monitors, check statuses, manage incidents, and more.

Supported clients

Any MCP-compatible AI client works with the WatchCron server. Tested with:

  • Claude Desktop — Anthropic's desktop app
  • Claude Code — CLI agent for software engineering
  • Cursor — AI-powered code editor
  • Windsurf — AI IDE by Codeium
  • ChatGPT (with MCP plugin support)
  • Any client that supports the MCP stdio transport

Installation

The MCP server is distributed as an npm package. No global installation required — use npx to run it directly:

Run with npx
npx watchcron-mcp

Or install globally:

Global install
npm install -g watchcron-mcp

Configuration

The MCP server needs your WatchCron API key. Pass it as an environment variable:

Claude Desktop

Add to your claude_desktop_config.json:

claude_desktop_config.json
{
  "mcpServers": {
    "watchcron": {
      "command": "npx",
      "args": ["watchcron-mcp"],
      "env": {
        "WATCHCRON_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Claude Code

Add via CLI
claude mcp add watchcron -- npx watchcron-mcp

Then set the environment variable in your shell profile or .env file:

Environment variable
export WATCHCRON_API_KEY="YOUR_API_KEY"

Cursor

Add to your .cursor/mcp.json in the project root:

.cursor/mcp.json
{
  "mcpServers": {
    "watchcron": {
      "command": "npx",
      "args": ["watchcron-mcp"],
      "env": {
        "WATCHCRON_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Windsurf

Add to your ~/.codeium/windsurf/mcp_config.json:

mcp_config.json
{
  "mcpServers": {
    "watchcron": {
      "command": "npx",
      "args": ["watchcron-mcp"],
      "env": {
        "WATCHCRON_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
Your API key is project-scoped. The MCP server can only access monitors, incidents, and channels within that project.

Available tools (43)

The MCP server exposes 43 tools covering all 9 API resource types. Each tool maps to one REST API endpoint. Your AI assistant discovers these tools automatically.

Cron Job Monitors (Checks)

ToolDescription
list_monitorsList all cron job checks with optional tag filter
create_monitorCreate a cron job check (simple or cron schedule)
get_monitorGet check details by UUID
update_monitorUpdate check settings
delete_monitorDelete a check and all ping data
pause_monitorPause or resume a check
get_pingsList ping history for a check

HTTP / Uptime Monitors

ToolDescription
list_http_monitorsList all HTTP monitors with optional status filter
create_http_monitorCreate an HTTP monitor (URL, keywords, SSL, thresholds)
get_http_monitorGet HTTP monitor details
update_http_monitorUpdate HTTP monitor settings
delete_http_monitorDelete an HTTP monitor
pause_http_monitorPause or resume an HTTP monitor
get_http_monitor_logsList check logs (status, response time, errors)

Cloud Cron Jobs

ToolDescription
list_cloud_cronsList all Cloud Cron jobs
create_cloud_cronCreate a scheduled HTTP job (cron expression, retries, overlap prevention)
get_cloud_cronGet Cloud Cron job details
update_cloud_cronUpdate a Cloud Cron job
delete_cloud_cronDelete a Cloud Cron job
pause_cloud_cronPause or resume a Cloud Cron job
get_cloud_cron_logsList execution logs

Port Monitors (TCP/UDP/DNS/ICMP)

ToolDescription
list_port_monitorsList all port monitors with optional type filter
create_port_monitorCreate a port monitor (TCP, UDP, DNS, or ICMP)
get_port_monitorGet port monitor details
delete_port_monitorDelete a port monitor
pause_port_monitorPause or resume a port monitor

Domain Monitors

ToolDescription
list_domain_monitorsList all domain expiration monitors
create_domain_monitorCreate a domain monitor with warning threshold
get_domain_monitorGet domain monitor details (registrar, expiry date)
delete_domain_monitorDelete a domain monitor

Blocklist Monitors

ToolDescription
list_blocklist_monitorsList all blocklist monitors
create_blocklist_monitorCreate a DNSBL monitor for an IP or hostname
get_blocklist_monitorGet blocklist monitor details
delete_blocklist_monitorDelete a blocklist monitor
list_incidents_logList blocklist scan logs

Incidents

ToolDescription
get_incidentsList incidents with status and active_only filters
create_incidentCreate an incident with title, severity, and initial message
get_incidentGet incident details with update timeline
update_incidentUpdate status, add timeline message, resolve
delete_incidentDelete an incident

Status Pages & Channels

ToolDescription
list_status_pagesList all status pages
get_status_pageGet status page details by slug
list_channelsList notification channels

Usage examples

Once configured, you can ask your AI assistant to manage monitors in natural language:

Example prompts
# Create a cron job monitor
"Create a check for my nightly backup that runs at 2 AM with a 10-minute grace period"

# Set up uptime monitoring
"Monitor https://api.example.com/health every minute, alert if it returns anything other than 200"

# Schedule a Cloud Cron job
"Set up a Cloud Cron to call my WordPress wp-cron.php every 5 minutes"

# Check port connectivity
"Create a TCP monitor for my database at db.example.com:5432"

# Monitor domain expiration
"Track when example.com expires and warn me 60 days before"

# Manage incidents
"Create a critical incident titled 'Database outage' with a message about connection failures"

# Check status
"Show me all monitors that are currently down"
"What's the uptime log for my production API monitor?"

How it works

The MCP server runs locally on your machine as a subprocess. When your AI assistant needs to interact with WatchCron, it:

  1. Discovers the available tools from the MCP server
  2. Decides which tool to call based on your request
  3. Sends structured parameters to the MCP server via stdio
  4. The MCP server calls the WatchCron REST API with your API key
  5. Results are returned to your AI assistant in a readable format

No data leaves your machine except the API calls to watchcron.com. The MCP server has no database, no state, and no background processes. It only runs when your AI client invokes it.

Troubleshooting

"Tool not found" or server not connecting

Make sure you have Node.js 18+ installed. Check that the config JSON path is correct for your client. Restart the AI client after changing the config.

Authentication errors

Verify your WATCHCRON_API_KEY is set correctly in the env block. The key must be a valid project-scoped API key from your dashboard. Test it with curl:

Test your API key
curl -H "Authorization: Bearer YOUR_API_KEY" \
     https://watchcron.com/api/v1/checks

Rate limiting

The MCP server uses the same rate limits as the REST API. If your AI agent makes too many calls in quick succession, requests may return 429 errors. See Rate limits for details per plan.

Pricing Docs
Log in Start free →