Rootly for AI agents
Rootly is an incident management platform that coordinates response workflows, tracking incidents and action items across tools like Slack and PagerDuty. 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 Rootly.
Check an incident's status
Get an incident's details to see its current severity and assigned responders.
Track a follow-up action item
List action items for an incident to confirm nothing is left open after it's resolved.
Confirm before deleting an incident
Get the incident's details first, then delete it only after confirming it was a duplicate.
6 Rootly actions, graded by risk.
Every Rootly 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.
- rootly.get_incidentGet Incident Details
- rootly.get_action_itemGet Action Item Details
- rootly.list_action_itemsList Action Items
write
1Create and change things. Allow, or ask the user first.
- rootly.update_incidentUpdate Incident
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- rootly.delete_incidentDelete Incident
- rootly.delete_action_itemDelete Action Item
Rootly in three steps.
- 01Your users connect RootlyThey add their Rootly api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “update Incident” can wait for the user, and “delete Incident” can be denied outright.
- 03Any agent can actYour agent calls Rootly through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('rootly', { read: 'allow', write: 'ask', // update_incident destructive: 'deny', // delete_incident }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Rootly connects.
Users add their Rootly 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 Rootly 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 Rootly from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Rootly and Arc0, answered.
Can I use Rootly with Claude, ChatGPT or Cursor?
Yes. Connect Rootly 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 Rootly actions you allow.
How do users connect Rootly?
Users add their Rootly 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 Rootly actions can my agent take?
6 in total: 3 read, 1 write and 2 destructive, such as “update Incident”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Rootly?
Yes. Actions like “delete Incident” 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 Rootly too?
Yes. The same Rootly connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Rootly into your agent.
Your users connect Rootly once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan