Peekaboo (macOS Screen Capture) logo

Peekaboo (macOS Screen Capture)

CommunityPopular
steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

Publishersteipete
Repositorypeekaboo
LanguageSwift
Forks
289
Stars
4K
Available tools
0
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    Peekaboo (macOS Screen Capture) exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    4K stars and 289 forks from the linked repository.

Peekaboo 🫣 - Mac automation that sees the screen and does the clicks.

Peekaboo Banner

npm package License: MIT macOS 15.0+ (Sequoia) Swift 6.2 node >=22 Download macOS Homebrew Ask DeepWiki

Peekaboo brings high-fidelity screen capture, AI analysis, and complete GUI automation to macOS. Version 3 adds native agent flows and multi-screen automation across the CLI and MCP server.

What you get

  • Pixel-accurate captures (windows, screens, menu bar) with optional Retina 2x scaling.
  • Natural-language agent that chains Peekaboo tools (see, click, type, scroll, hotkey, menu, window, app, dock, space).
  • Action-first UI automation for routine clicks/scrolls, with synthetic input fallback for apps that need it.
  • Direct accessibility tools for settable values and named actions (set-value, perform-action).
  • Menu and menubar discovery with structured JSON; no clicks required.
  • Multi-provider AI: GPT-5.1 family, Claude 4.x, Grok 4-fast (vision), Gemini 2.5, and local Ollama models.
  • MCP server for Codex, Claude Code, and Cursor plus a native CLI; the same tools in both.
  • Configurable, testable workflows with reproducible sessions and strict typing.
  • Requires macOS Screen Recording + Accessibility permissions (see docs/permissions.md).

Install

  • macOS app + CLI (Homebrew):
    bash
    brew install steipete/tap/peekaboo
  • MCP server (Node 22+, no global install needed):
    bash
    npx -y @steipete/peekaboo

Quick start

bash
# Capture full screen at Retina scale and save to Desktop
peekaboo image --mode screen --retina --path ~/Desktop/screen.png

# Click a button by label (captures, resolves, and clicks in one go)
peekaboo see --app Safari --json | jq -r '.data.snapshot_id' | read SNAPSHOT
peekaboo click --on "Reload this page" --snapshot "$SNAPSHOT"

# Directly set a text field value when the accessibility value is settable
peekaboo set-value --on T1 --value "hello" --snapshot "$SNAPSHOT"

# Invoke a named accessibility action on an element
peekaboo perform-action --on B1 --action AXPress --snapshot "$SNAPSHOT"

# Run a natural-language automation
peekaboo agent "Open Notes and create a TODO list with three items"

# Run as an MCP server (Codex, Claude Code, Cursor)
npx -y @steipete/peekaboo

# Minimal MCP client config snippet:
# {
#   "mcpServers": {
#     "peekaboo": {
#       "command": "npx",
#       "args": ["-y", "@steipete/peekaboo"],
#       "env": {
#         "PEEKABOO_AI_PROVIDERS": "openai/gpt-5.5,anthropic/claude-opus-4-7"
#       }
#     }
#   }
# }

Shell completions

Peekaboo can generate shell-native completions directly from the same Commander metadata that powers CLI help and docs:

bash
# Current shell (recommended)
eval "$(peekaboo completions $SHELL)"

# Explicit shells
eval "$(peekaboo completions zsh)"
eval "$(peekaboo completions bash)"
peekaboo completions fish | source

For persistent setup and troubleshooting, see docs/commands/completions.md.

CommandKey flags / subcommandsWhat it does
see--app, --mode screen/window, --retina, --jsonCapture and annotate UI, return snapshot + element IDs
click--on <id/query>, --snapshot, --wait-for, --coordsClick by element ID, label, or coordinates
type--text, --clear, --profile, --delayEnter text with pacing options
set-value--on <id/query>, --value, --snapshotDirectly set a settable accessibility value
perform-action--on <id/query>, --action, --snapshotInvoke a named accessibility action
presskey names, --count, --delay, --holdSpecial keys and sequences
hotkeycombos like cmd,shift,tModifier combos (cmd/ctrl/alt/shift)
scroll--on <id>, --direction up/down, --amountScroll views or elements
swipe--from/--to, --duration, --stepsSmooth gesture-style drags
drag--from/--to, modifiers, Dock/Trash targetsDrag-and-drop between elements/coords
move--to <id/coords>, --screen-indexPosition the cursor without clicking
windowlist, move, resize, focus, set-boundsMove/resize/focus windows and Spaces
applaunch, quit, relaunch, switch, listLaunch, quit, relaunch, switch apps
spacelist, switch, move-windowList or switch macOS Spaces
menulist, list-all, click, click-extraList/click app menus and extras
menubarlist, clickTarget status-bar items by name/index
docklaunch, right-click, hide, show, listInteract with Dock items
dialoglist, click, input, file, dismissDrive system dialogs (open/save/etc.)
image--mode screen/window/menu, --retina, --analyzeScreenshot screen/window/menu bar (+analyze)
listapps, windows, screens, menubar, permissionsEnumerate apps, windows, screens, permissions
tools--verbose, --json, --no-sortInspect native Peekaboo tools
completions[shell]Generate zsh/bash/fish completion scripts from Commander metadata
configinit, show, add, login, modelsManage credentials/providers/settings
permissionsstatus, grantCheck/grant required macOS permissions
run.peekaboo.json, --output, --no-fail-fastExecute .peekaboo.json automation scripts
sleep--duration (ms)Millisecond delays between steps
clean--all-snapshots, --older-than, --snapshotPrune snapshots and caches
agent--model, --dry-run, --resume, --max-steps, audioNatural-language multi-step automation
mcpserve (default)Run Peekaboo as an MCP server

Models and providers

  • OpenAI: GPT-5.1 (default) and GPT-4.1/4o vision
  • Anthropic: Claude 4.x
  • xAI: Grok 4-fast reasoning + vision
  • Google: Gemini 2.5 (pro/flash)
  • Local: Ollama (llama3.3, llava, etc.)

Set providers via PEEKABOO_AI_PROVIDERS or peekaboo config add.

Learn more

Community

Development basics

  • Requirements: macOS 15+, Xcode 16+/Swift 6.2. Node 22+ only if you run the pnpm docs/build helper scripts (core CLI/app/MCP are Swift-only).
  • Install deps: pnpm install then pnpm run build:cli or pnpm run test:safe.
  • Lint/format: pnpm run lint && pnpm run format.

License

MIT

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "peekaboo": {
      "command": "npx",
      "args": [
        "-y",
        "@steipete/peekaboo-mcp"
      ],
      "env": {
        "PEEKABOO_AI_PROVIDERS": "openai/gpt-4o,ollama/llava:latest",
        "OPENAI_API_KEY": "your-openai-api-key-here"
      }
    }
  }
}

Use Peekaboo (macOS Screen Capture) MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Peekaboo (macOS Screen Capture) is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Peekaboo (macOS Screen Capture) as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Peekaboo (macOS Screen Capture) MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "peekaboo-macos-screen-capture": {
      "command": "npx",
      "args": [
        "-y",
        "@steipete/peekaboo-mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Peekaboo (macOS Screen Capture) MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Peekaboo (macOS Screen Capture) MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Peekaboo (macOS Screen Capture) to help me with this task?
Peekaboo (macOS Screen Capture)
Sure. I read it.
Here is what I found using Peekaboo (macOS Screen Capture).

Frequently asked questions

What is the Peekaboo (macOS Screen Capture) MCP server used for?

Peekaboo (macOS Screen Capture) is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Peekaboo (macOS Screen Capture) MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Peekaboo (macOS Screen Capture) with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Peekaboo (macOS Screen Capture) MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Peekaboo (macOS Screen Capture) connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Peekaboo (macOS Screen Capture) MCP to TypingMind?

Peekaboo (macOS Screen Capture) runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Peekaboo (macOS Screen Capture) MCP provide in TypingMind?

Peekaboo (macOS Screen Capture) exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Peekaboo (macOS Screen Capture) MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Peekaboo (macOS Screen Capture) requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇