Pushinator for AI agents
Pushinator provides push notification channels for sending real-time alerts to subscribed users and devices. Developers use it for lightweight app or service notifications. 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 Pushinator.
Send a notification to a channel
Push an alert to all subscribers of a channel when an event occurs.
Check a channel's details read-only
Look up a channel's configuration before sending a notification through it.
Delete a channel with approval
Remove a notification channel only after confirming no service still publishes to it.
7 Pushinator actions, graded by risk.
Every Pushinator 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.
- pushinator.get_channelGet Channel
- pushinator.list_channelsList Channels
- pushinator.get_current_userGet Current User
write
3Create and change things. Allow, or ask the user first.
- pushinator.create_channelCreate Channel
- pushinator.update_channelUpdate Channel
- pushinator.send_notificationSend Notification
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- pushinator.delete_channelDelete Channel
Pushinator in three steps.
- 01Your users connect PushinatorThey add their Pushinator api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Channel” can wait for the user, and “delete Channel” can be denied outright.
- 03Any agent can actYour agent calls Pushinator through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('pushinator', { read: 'allow', write: 'ask', // create_channel destructive: 'deny', // delete_channel }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Pushinator connects.
Users add their Pushinator 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 Pushinator 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 Pushinator from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Pushinator and Arc0, answered.
Can I use Pushinator with Claude, ChatGPT or Cursor?
Yes. Connect Pushinator 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 Pushinator actions you allow.
How do users connect Pushinator?
Users add their Pushinator 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 Pushinator actions can my agent take?
7 in total: 3 read, 3 write and 1 destructive, such as “create Channel”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Pushinator?
Yes. Actions like “delete Channel” 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 Pushinator too?
Yes. The same Pushinator connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Pushinator into your agent.
Your users connect Pushinator once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan