What tools does MacOS Clipboard MCP expose?
It exposes three MCP tools: `copy_to_clipboard(data: str)`, `paste_from_clipboard()` (returns text), and `paste_image_from_clipboard()` (returns the clipboard image as a base64‑encoded PNG string).
@xiaoquisme
Basic information
A simple utility that provides model context protocol (MCP) tools for interacting with the macOS clipboard.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"macos-cliboard-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MacOS Clipboard MCP is a Model Context Protocol server that exposes tools for reading and writing the macOS clipboard. It is built for developers who want to let AI assistants or MCP-compatible clients copy text to, paste text from, or retrieve images from the system clipboard on macOS.
The recommended setup uses uvx with no local install: add an MCP client entry with command uvx and args ["macos-clipboard-mcp"]. Alternatively, clone the repo, run uv sync, and start the server with mcp dev main.py. The server exposes three tools: copy_to_clipboard, paste_from_clipboard, and paste_image_from_clipboard.
uvx one‑command approachIt exposes three MCP tools: `copy_to_clipboard(data: str)`, `paste_from_clipboard()` (returns text), and `paste_image_from_clipboard()` (returns the clipboard image as a base64‑encoded PNG string).
Python 3.12 or later and macOS are required. Clipboard operations are implemented via AppleScript, so the server will not function on other operating systems.
The server relies on macOS AppleScript to read from and write to the system clipboard. No external GUI or X11 dependency is needed.
The server supports TIFF, PNG, and JPEG image formats currently in the clipboard. The output is always a base64‑encoded PNG.
The recommended method adds a `clipboard` entry with `"command": "uvx"` and `"args": ["macos-clipboard-mcp"]`. An alternative method uses `"command": "uv"` with local folder arguments pointing to a cloned copy of the repository.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
MCP Toolbox for Databases is an open source MCP server for databases.
🚀 The fast, Pythonic way to build MCP servers and clients.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
Comments