Pushover for AI agents
Pushover delivers real-time notifications to a person's devices through a simple API integration. Developers and sysadmins use it to get alerted about scripts, servers, and monitoring events. 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 Pushover.
Send a message notification
Send an alert message to a user's devices when a monitored event happens.
Check receipt status read-only
Look up whether an emergency-priority message has been acknowledged yet.
Cancel retries with approval
Stop retrying a message's delivery only after confirming the issue is resolved.
29 Pushover actions, graded by risk.
Every Pushover action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- pushover.get_app_tokenGet Application Token
- pushover.get_app_limitsGet App Limits
- pushover.get_app_icon_imageGet Application Icon Image
- pushover.get_receipt_statusGet Receipt Status
- pushover.get_team_api_tokenGet Team API Token
- pushover.validate_user_or_groupValidate User or Group
write
17Create and change things. Allow, or ask the user first.
- pushover.send_messageSend Message
- pushover.group_getGet Group Details
- pushover.group_listList Delivery Groups
- pushover.client_loginPushover Client Login
- pushover.group_createCreate Group
- pushover.group_renameRename Delivery Group
- pushover.glances_updateGlances Update
- pushover.group_add_userAdd User to Group
- pushover.license_assignAssign License
- pushover.teams_add_userAdd Team User
- pushover.group_enable_userGroup Enable User
- pushover.subscription_flowSubscription Flow
- pushover.store_team_api_tokenStore Team API Token
- pushover.client_fetch_messagesFetch Pending Messages
- pushover.license_check_creditsCheck License Credits
- pushover.client_register_deviceRegister Open Client Device
destructive
6Delete, cancel or archive. Ask first, or deny outright.
- pushover.cancel_retries_by_tagCancel Retries by Tag
- pushover.cancel_receipt_retriesCancel Receipt Retries
- pushover.group_remove_userRemove User from Group
- pushover.teams_remove_userRemove User from Team
- pushover.group_disable_userDisable Group User
- pushover.client_ack_delete_up_to_idClient Acknowledge Delete Up To ID
Pushover in three steps.
- 01Your users connect PushoverThey add their Pushover api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “send Message” can wait for the user, and “cancel Retries by Tag” can be denied outright.
- 03Any agent can actYour agent calls Pushover through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('pushover', { read: 'allow', write: 'ask', // send_message destructive: 'deny', // cancel_retries_by_tag }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Pushover connects.
Users add their Pushover 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 Pushover 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 Pushover from any agent.
Pushover and Arc0, answered.
Can I use Pushover with Claude, ChatGPT or Cursor?
Yes. Connect Pushover 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 Pushover actions you allow.
How do users connect Pushover?
Users add their Pushover 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 Pushover actions can my agent take?
29 in total: 6 read, 17 write and 6 destructive, such as “send Message”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Pushover?
Yes. Actions like “cancel Retries by Tag” 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 Pushover too?
Yes. The same Pushover connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Pushover into your agent.
Your users connect Pushover once, under your brand. Your agent gets 29 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan