# Overview

Source: https://pushary.com/docs/agents
Last updated: 2026-11-01

> Push notifications, permission approvals and human in the loop for AI agents. Approve risky actions and answer your agent's questions from your phone.

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:

```bash
npx pushary@latest setup
```

It finds your agents, connects them, saves your API key and pairs your phone.

<Cards>
  <Card title="Start the quickstart" description="The full setup, step by step, from install to your first approval on your phone." href="/docs/agents/quickstart" />
</Cards>

## What you can do [#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](/docs/agents/policies) decide which actions run on their own and which ask you.
* **Stop a runaway agent.** The [kill switch](/docs/agents/kill-switch) denies every action that session tries for the next hour.
* **See what happened.** The [audit log](/docs/agents/audit-log) keeps every question, answer and decision.

## How it works [#how-it-works]

```text
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](https://modelcontextprotocol.io). 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](/docs/agents/how-it-works), or see [which agents support hooks](/docs/agents/supported-agents).

## Set up your agent [#set-up-your-agent]

<Cards>
  <Card title="Claude Code" description="Hooks plus MCP tools. Approvals for shell commands, writes and edits." href="/docs/agents/guides/claude-code" />

  <Card title="Codex" description="Hooks plus MCP tools. Approvals for shell commands and file edits." href="/docs/agents/guides/codex" />

  <Card title="Gemini CLI" description="Hooks plus MCP tools. Approvals for shell commands, writes and edits." href="/docs/agents/guides/gemini-cli" />

  <Card title="Cursor" description="A plugin that holds shell commands and file edits for your approval, or plain MCP for notifications." href="/docs/agents/guides/cursor" />

  <Card title="Hermes" description="A Python plugin with error alerts and phone approval for dangerous commands." href="/docs/agents/guides/hermes" />

  <Card title="Mac app (Pushary Isle)" description="Questions show up in your Mac's notch. Answer with one key. No command needed." href="/docs/agents/mac-app" />

  <Card title="Claude" description="Add Pushary as a connector in Claude.ai, Claude Desktop or Cowork." href="/docs/agents/guides/claude-desktop" />

  <Card title="ChatGPT" description="Add Pushary as a connector so ChatGPT can notify you and ask you questions." href="/docs/agents/guides/chatgpt" />

  <Card title="Grok Bot" description="Add Pushary as a custom MCP server so your Bots notify you and ask you questions." href="/docs/agents/guides/grok-bot" />

  <Card title="Any other agent" description="Plain MCP, or a REST call from n8n, Zapier, scripts or any language." href="/docs/agents/connect-any-agent" />
</Cards>

See every agent and what Pushary can enforce for it on [Supported agents](/docs/agents/supported-agents).

## Build approvals into your product [#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.

<Cards>
  <Card title="Build approvals into your agent" description="Add a human approval step with the AI SDK, LangGraph, OpenAI Agents, Mastra or plain HTTP." href="/docs/agents/build/quickstart" />
</Cards>