Pingdom for AI agents
Pingdom monitors uptime and performance for websites, servers, and applications, alerting teams when something goes down. Ops teams use it to catch outages before customers report them. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Pingdom.
Check a site's uptime status
Look up a single check's current status read-only to confirm a site is responding.
Review recent maintenance windows
List maintenance windows to see if a reported outage overlaps planned downtime.
Check contact alert settings
Look up contact details read-only before confirming who gets paged for a new check.
13 Pingdom actions, graded by risk.
Every Pingdom action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
13Look things up. Allowed by default.
- pingdom.get_teamsGet Teams
- pingdom.get_probesGet Probes
- pingdom.get_creditsGet Credits
- pingdom.get_contactsGet Contacts
- pingdom.get_checks_listGet Checks List
- pingdom.get_single_checkGet Single Check
- pingdom.get_team_detailsGet Team Details
- pingdom.get_actions_alertsGet Pingdom Alert Actions
- pingdom.get_reference_dataGet Reference Data
- pingdom.get_contact_detailsGet Contact Details
- pingdom.get_maintenance_windowsGet Maintenance Windows
- pingdom.get_tms_transaction_checks_listGet TMS Transaction Checks List
- pingdom.get_list_maintenance_occurrencesList Maintenance Occurrences
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Pingdom in three steps.
- 01Your users connect PingdomThey add their Pingdom api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Pingdom through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('pingdom', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Pingdom connects.
Users add their Pingdom api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Pingdom connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Pingdom from any agent.
Pingdom and Arc0, answered.
Can I use Pingdom with Claude, ChatGPT or Cursor?
Yes. Connect Pingdom to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Pingdom actions you allow.
How do users connect Pingdom?
Users add their Pingdom api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Pingdom actions can my agent take?
13 in total: 13 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Pingdom?
Yes. Allow read actions and deny writes in the Pingdom policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Pingdom too?
Yes. The same Pingdom connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Pingdom into your agent.
Your users connect Pingdom once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan