AI Agent
Annotate
A macOS menu-bar app that gives AI agents the ability to draw directly on your screen via MCP.
Annotate
What is Annotate?
Annotate is a macOS menu-bar application that allows AI agents to draw directly on the user's screen using the Model Context Protocol (MCP). It provides a set of annotation tools (circle, underline, highlight, arrow, text, locate) and requires accessibility permissions but no network connections.
Annotate vs Similar AI Tools
| Pricing Model | Free | Free, Freemium | Free | Free |
| Free Credits | ||||
| Key Features |
|
|
|
|
| Pros |
|
|
|
|
| Cons |
|
|
|
|
| Best For |
|
|
|
|
How to use Annotate?
- 1Download and install the latest release from GitHub.
- 2Tell your AI agent to install the MCP tools via the provided URL.
- 3Let your agent paint by using the annotate tools to learn new apps, get pointers, or find help.
Annotate Key Features
- Annotate circles for looping with labels
- Underline phrases while keeping text readable
- Highlight regions with marker effect
- Arrow tool to point at elements
- Text tool for custom labels
- Locate tool to get real element positions
- Screen detection (multiple displays, scale)
- Clear tool to erase all annotations
- MCP server built into the app bundle
Annotate Use Cases
- Learning new software (e.g., Blender) with visual guidance
- Getting pointers in games (e.g., tower defence)
- Explaining complex ideas by pointing on screen
- AI-assisted tutorials and walkthroughs
Annotate Pricing & Free Credits
Annotate currently operates on a Free model.
This tool is completely free to use
Annotate Pros & Cons
Pros
- Completely free and open-source (MIT)
- Privacy-friendly – no network connections or screen captures
- Easy MCP integration with popular AI tools (Claude, Cursor, etc.)
- Deterministic drawing that can be tested offline
Cons
- macOS only (requires macOS 14+)
- Requires accessibility permissions to read UI elements
- Limited to drawing and locating – no screen capturing
What is Annotate best for?
- AI developers integrating screen annotation into workflows
- Educators creating interactive tutorials with AI agents
- Gamers needing visual cues from AI assistants