Updown.io for AI agents
updown.io monitors website and API uptime, used by developers who want a simple alert when a site goes down or slows down. 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 Updown.io.
List all checks
Pull the current list of monitored checks and their status, a read-only overview.
List monitoring nodes
Read which nodes are available for running checks from different regions.
Review a check before escalating
Look at a specific check's recent history before deciding whether to alert the team.
5 Updown.io actions, graded by risk.
Every Updown.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- updown_io.list_nodesList Monitoring Nodes
- updown_io.list_checksList All Checks
- updown_io.list_node_ipsList Node IPs
- updown_io.list_node_ipv4List node IPv4 addresses
- updown_io.list_node_ipv6List IPv6 nodes
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.
Updown.io in three steps.
- 01Your users connect Updown.ioThey add their Updown.io 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 Updown.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('updown_io', { 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 Updown.io connects.
Users add their Updown.io 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 Updown.io 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 Updown.io from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Updown.io and Arc0, answered.
Can I use Updown.io with Claude, ChatGPT or Cursor?
Yes. Connect Updown.io 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 Updown.io actions you allow.
How do users connect Updown.io?
Users add their Updown.io 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 Updown.io actions can my agent take?
5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Updown.io?
Yes. Allow read actions and deny writes in the Updown.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Updown.io too?
Yes. The same Updown.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Updown.io into your agent.
Your users connect Updown.io once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan