OpenPingGet early access
Build with it

MCP server

Add OpenPing to Claude, Cursor or any MCP client, then say what you want watched. Everything in the app is also here, so an assistant can set up and read monitoring for you.

The address

https://mcp.openping.ai

A remote server over Streamable HTTP. There is nothing to install.

Signing in

For now, the server takes an API key as the bearer token. OAuth sign-in is planned. Until then, make a key in the app under API keys and give it only the scopes you want the assistant to have: a read key can look but not change anything.

One tool needs no key: is_it_up answers whether any public site is up. It is also served on its own at https://mcp.openping.ai/public, for assistants that only need that.

Add it

Claude Code:

claude mcp add --transport http openping https://mcp.openping.ai \
  --header "Authorization: Bearer $OPENPING_API_KEY"

Clients that read a JSON config (Cursor and others):

mcp.json
{
  "mcpServers": {
    "openping": {
      "url": "https://mcp.openping.ai",
      "headers": { "Authorization": "Bearer opk_your_key_here" }
    }
  }
}

Then say

  • “Watch yourapp.com and tell me in Slack if it breaks.”
  • “Is anything down right now?”
  • “Add a test that asks my agent for the refund window and checks it says 30 days.”
  • “Draft a status update for the open incident.”

The tools

ToolWhat it doesChanges things?
discoverLook at a URL and suggest monitors, and say whether anything there is written to steer an AI. Creates nothingNo, read-only
create_monitorsCreate monitors from the suggestions or from a spec, after you confirmYes
list_monitorsEvery monitor with its stateNo, read-only
get_monitorOne monitor: state, recent runs, uptimeNo, read-only
get_statusIs everything up? Counts by state, what is not up and since when, open incidents, status pagesNo, read-only
run_checkRun one check now and return the resultYes, it runs a real check
list_incidentsOpen and recent incidentsNo, read-only
get_incidentOne incident with its summary and timelineNo, read-only
acknowledge_alertSay “I’m on it”, which stops the escalationYes
draft_status_updateWrite a status update in plain wordsNo, it posts nothing
post_status_updatePost an update to the status page. Always needs your yesYes, in public
add_agent_testAdd a test case in plain wordsYes
create_status_pageMake a status page from your monitors. It stays private until a person publishes itYes
run_site_checkCheck a site you own: what it runs on and depends on, what to fix first, and monitors to add. Reads only what a visitor's browser wouldNo, read-only
get_site_checkRead a site check's report, or list recent onesNo, read-only
run_go_liveIs a site ready to go live? Pass or blocked, a grade, the blockers with copy-paste fixes, and the monitors to keepNo, read-only
list_inboxYour inbox: every alert, recovery and update OpenPing sent you, unread firstNo, read-only
who_is_on_callWho is on call now for each schedule, until when, and who is nextNo, read-only
is_it_upIs any public site up right now: up, slow or down, 30 days of uptime and recent trouble. Needs no keyNo, read-only

What keeps it safe

  • Read tools are marked read-only. Tools that change things carry the hints that make clients ask you first.
  • post_status_update never posts on an assistant’s say-so alone. It needs your yes, every time.
  • The server holds nothing itself. It passes your key straight to the API, which enforces the key’s scopes.

Building an agent?

See for AI agents: what each tool needs, which key scopes, and what needs a person’s yes.

We watch it with OpenPing

OpenPing’s own MCP server is watched by an MCP monitor, like any other.