Cronly for AI agents
Cronly monitors cron jobs, SSL certificates, and servers, alerting a team when a scheduled task silently fails or a certificate is about to expire. 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 Cronly.
Check a monitor's status
Check a monitor's status to see whether its last expected run actually came in.
Create a certificate monitor
Create a monitor tracking an SSL certificate's expiration date for a domain.
Confirm before deleting a monitor
Confirm before deleting a monitor, since alerts for that job or certificate stop immediately.
10 Cronly actions, graded by risk.
Every Cronly action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- cronly.get_companyGet Company
- cronly.get_resourceGet Resource
- cronly.list_resourcesList Resources
write
4Create and change things. Allow, or ask the user first.
- cronly.create_monitorCreate Monitor
- cronly.create_projectCreate Project
- cronly.create_certificateCreate Certificate Monitor
- cronly.pulse_monitorPulse Monitor
destructive
3Delete, cancel or archive. Ask first, or deny outright.
- cronly.delete_monitorDelete Monitor
- cronly.delete_projectDelete Project
- cronly.delete_certificateDelete Certificate Monitor
Cronly in three steps.
- 01Your users connect CronlyThey add their Cronly api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Monitor” can wait for the user, and “delete Monitor” can be denied outright.
- 03Any agent can actYour agent calls Cronly through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('cronly', { read: 'allow', write: 'ask', // create_monitor destructive: 'deny', // delete_monitor }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Cronly connects.
Users add their Cronly 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 Cronly 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 Cronly from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Cronly and Arc0, answered.
Can I use Cronly with Claude, ChatGPT or Cursor?
Yes. Connect Cronly 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 Cronly actions you allow.
How do users connect Cronly?
Users add their Cronly 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 Cronly actions can my agent take?
10 in total: 3 read, 4 write and 3 destructive, such as “create Monitor”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Cronly?
Yes. Actions like “delete Monitor” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Cronly too?
Yes. The same Cronly connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Cronly into your agent.
Your users connect Cronly once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan