@SeanFDZ
Basic information
Let AI agents control Classic Mac OS through a shared folder protocol.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"classic-mac": {
"command": "node",
"args": [
"/path/to/mcp-server/dist/server.js",
"--config",
"/path/to/fleet.json"
]
}
}
}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.
AgentBridge is a native Classic Mac OS application that lets AI agents (like Claude) interact with Mac OS 7–9 through structured commands and responses. It uses a shared folder for transport, works on real hardware and emulators, and requires no modifications to the Classic Mac.
Install the MCP server via npm (npm install -g classic-mac-mcp) or run with npx, create a fleet.json configuration file pointing to the shared folder, then launch AgentBridge on the Classic Mac. AI agents can then send commands (e.g., ping) via files in the inbox, and AgentBridge writes responses to the outbox.
AgentBridge uses a shared folder as its transport. Commands are written to an `inbox` folder, and responses are read from an `outbox` folder. The folder can be on a NAS, emulator host directory, or any shared filesystem both sides can access.
AgentBridge requires System 7.0 or later (for Apple Events support). It has been tested on System 7.6.1 (68k) and builds for PowerPC Mac OS 8.5–9.2.2.
Yes. Each Mac gets its own subfolder (e.g., `AgentBridge-SE30`) with its own inbox/outbox/assets. The MCP server’s `fleet.json` configuration can list multiple targets, and tools accept an optional `target` parameter.
No. AgentBridge is a regular application — launch it, quit it, done. No SSH, drivers, or system extensions are required.
The server exposes tools for system status (ping, heartbeat, system info), windows/processes, menus, mouse/keyboard, clipboard, application control, and file/volume browsing. A full list is in the MCP Tools Reference section of the README.
🚀 The fast, Pythonic way to build MCP servers and clients.
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
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.
Comments