Webpushr for AI agents
Webpushr sends browser push notifications from a website to subscribers, used by publishers and marketers re-engaging visitors after they leave the site. 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 Webpushr.
Check subscriber count
Read the current number of push subscribers, a read-only audience check.
Send a notification to a segment
Push a notification to a specific audience segment rather than everyone.
Confirm before sending to all subscribers
Get approval before sending a notification to every subscriber, since it reaches the full audience at once.
6 Webpushr actions, graded by risk.
Every Webpushr action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- webpushr.get_subscriber_countGet Subscriber Count
- webpushr.get_notification_statusGet Notification Status
write
4Create and change things. Allow, or ask the user first.
- webpushr.send_notification_to_allSend Notification to All Subscribers
- webpushr.send_notification_to_segmentsSend Notification to Segments
- webpushr.send_notification_to_attributesSend Notification by Attributes
- webpushr.send_notification_to_subscriberSend Notification to Subscriber
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Webpushr in three steps.
- 01Your users connect WebpushrThey add their Webpushr api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send Notification to All Subscribers” can wait for the user to approve.
- 03Any agent can actYour agent calls Webpushr through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('webpushr', { read: 'allow', write: 'ask', // send_notification_to_all destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Webpushr connects.
Users add their Webpushr 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 Webpushr 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 Webpushr from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Webpushr and Arc0, answered.
Can I use Webpushr with Claude, ChatGPT or Cursor?
Yes. Connect Webpushr 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 Webpushr actions you allow.
How do users connect Webpushr?
Users add their Webpushr 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 Webpushr actions can my agent take?
6 in total: 2 read, 4 write and 0 destructive, such as “send Notification to All Subscribers”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Webpushr?
Yes. Allow read actions and deny writes in the Webpushr policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Webpushr too?
Yes. The same Webpushr connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Webpushr into your agent.
Your users connect Webpushr 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