PushAlert for AI agents

PushAlert sends and manages web push notifications along with subscriber segments and automation for a website. Marketing teams use it to re-engage site visitors with timely alerts. 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.

CommunicationAPI keyMCP + RESTpushalert.co
AUDIT LOG · PUSHALERTPOLICY: acme-support
09:41:07 · claude · u_8f2read
pushalert.list_segments
List Segments✓ allowed · 212ms
09:41:08 · claude · u_8f2read
pushalert.get_notification_stats
Get Notification Stats✓ allowed · 164ms
09:41:09 · claude · u_8f2write
pushalert.create_segment
Create Segment✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
pushalert.delete_segment
Delete Segment✕ blocked · policy: deny
EVERY PUSHALERT CALL, ON THE RECORD
01 · USE CASES

What agents do in PushAlert.

01

Send a web push notification

Push a notification to a subscriber segment about a sale or new content.

02

Check notification stats read-only

Pull delivery and click stats for a sent notification to gauge its performance.

03

Delete a segment with approval

Remove a subscriber segment only after confirming it is no longer used in campaigns.

02 · ACTIONS

9 PushAlert actions, graded by risk.

Every PushAlert action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

3

Look things up. Allowed by default.

  • pushalert.list_segments
    List Segments
  • pushalert.get_notification_stats
    Get Notification Stats
  • pushalert.get_subscriber_attributes
    Get Subscriber Attributes

write

4

Create and change things. Allow, or ask the user first.

  • pushalert.create_segment
    Create Segment
  • pushalert.add_subscribers_to_segment
    Add Subscribers to Segment
  • pushalert.send_web_push_notification
    Send Web Push Notification
  • pushalert.set_subscriber_attributes
    Set Subscriber Attributes

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • pushalert.delete_segment
    Delete Segment
  • pushalert.remove_subscribers_from_segment
    Remove Subscribers from Segment
03 · HOW IT WORKS

PushAlert in three steps.

  1. 01Your users connect PushAlertThey add their PushAlert api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Segment” can wait for the user, and “delete Segment” can be denied outright.
  3. 03Any agent can actYour agent calls PushAlert through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('pushalert', {
  read: 'allow',
  write: 'ask',        // create_segment
  destructive: 'deny',  // delete_segment
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How PushAlert connects.

Users add their PushAlert 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 PushAlert 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
05 · WORKS WITH

Use PushAlert from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

PushAlert and Arc0, answered.

Q01

Can I use PushAlert with Claude, ChatGPT or Cursor?

Yes. Connect PushAlert 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 PushAlert actions you allow.

Q02

How do users connect PushAlert?

Users add their PushAlert 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.

Q03

Which PushAlert actions can my agent take?

9 in total: 3 read, 4 write and 2 destructive, such as “create Segment”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in PushAlert?

Yes. Actions like “delete Segment” 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.

Q05

Can my own backend call PushAlert too?

Yes. The same PushAlert connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug PushAlert into your agent.

Your users connect PushAlert once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan