Overview
Push notifications, permission approvals and human in the loop for AI agents. Approve risky actions and answer your agent's questions from your phone.
Updated
Pushary connects your AI agents to your phone. When Claude Code, Codex, Cursor or another agent needs a yes before a risky step, or sends you an update such as a finished task, your phone buzzes. You tap Approve or Deny, or type an answer, and the agent keeps going. You do not have to sit and watch the terminal.
Run this on the computer where your agent runs:
npx pushary@latest setupIt finds your agents, connects them, saves your API key and pairs your phone.
Start the quickstart
The full setup, step by step, from install to your first approval on your phone.
What you can do
- Walk away while an agent works. Your phone buzzes when the task is done or something breaks.
- Approve risky actions before they run. The agent wants to run
rm -rf ./dist? You see the exact command and tap Approve or Deny. - Answer questions from anywhere. Pick an option or type a reply on your phone.
- Set rules once. Policies decide which actions run on their own and which ask you.
- Stop a runaway agent. The kill switch denies every action that session tries for the next hour.
- See what happened. The audit log keeps every question, answer and decision.
How it works
Your agent -> Pushary -> Your phone (or your Mac)Pushary works in two ways. Setup turns on both where your agent supports them.
- Tools. Pushary runs a hosted MCP server. MCP is a standard way for an agent to call outside tools. Your agent gets tools to notify you and ask you questions. Any MCP client can use them, and the agent decides when to call them.
- Hooks. Some agents, such as Claude Code, Codex, Gemini CLI and Cursor, let another program check an action before it runs. Pushary uses these hooks to hold a risky action until you answer, so the agent cannot run it first. If Pushary cannot be reached, the agent's own prompt decides instead.
Read how it works in detail, or see which agents support hooks.
Set up your agent
Claude Code
Hooks plus MCP tools. Approvals for shell commands, writes and edits.
Codex
Hooks plus MCP tools. Approvals for shell commands and file edits.
Gemini CLI
Hooks plus MCP tools. Approvals for shell commands, writes and edits.
Cursor
A plugin that holds shell commands and file edits for your approval, or plain MCP for notifications.
Hermes
A Python plugin with error alerts and phone approval for dangerous commands.
Mac app (Pushary Isle)
Questions show up in your Mac's notch. Answer with one key. No command needed.
Claude
Add Pushary as a connector in Claude.ai, Claude Desktop or Cowork.
ChatGPT
Add Pushary as a connector so ChatGPT can notify you and ask you questions.
Grok Bot
Add Pushary as a custom MCP server so your Bots notify you and ask you questions.
Any other agent
Plain MCP, or a REST call from n8n, Zapier, scripts or any language.
See every agent and what Pushary can enforce for it on Supported agents.
Build approvals into your product
Your own agent can ask your users before it sends a refund, an email or a delete. They tap Approve or Deny on their phone.