A2A Governance Bridge MCP server. Tools: verify agent compliance, authorize a2a transaction, get trust registry. Built by MEOK AI Labs.
Classic Mac is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open InstallationWhat it does
MCP server for controlling Classic Mac OS targets (emulated and real hardware)
Quickstart
# 1 — run it from where its publisher ships it
npx -y classic-mac-mcp
# 2 — ask your agent something
> MCP server for controlling Classic Mac OS targets (emulated and real hardware)
Classic Mac is free: there is no plan to choose, no cap to set and nothing that can bill you.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Classic Mac as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add classic-mac-mcp -- npx -y classic-mac-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List all Classic Mac targets in the fleet with their current status,
Takes no parameters.
Ping a Classic Mac target to check if AgentBridge is responding.
Takes no parameters.
Read the heartbeat status of a Classic Mac target. Returns uptime,
Takes no parameters.
List all visible windows on a Classic Mac target. Returns window title,
Takes no parameters.
List running applications on a Classic Mac target. Returns app name,
Takes no parameters.
List the menu bar contents for the frontmost application.
Takes no parameters.
Get all items in a specific menu, including enabled/disabled state
Takes no parameters.
Get detailed info about the frontmost window: title, app, bounds.
Takes no parameters.
List mounted volumes (disks) with free and total space. Requires AgentBridge.
Takes no parameters.
List contents of a folder on the Classic Mac. Returns file names,
Takes no parameters.
Get system information about a Classic Mac target: OS version,
Takes no parameters.
Read the clipboard (scrap) contents as text. Requires AgentBridge.
Takes no parameters.
Set the clipboard (scrap) to the given text. Useful for pasting
Takes no parameters.
Click at screen coordinates on a Classic Mac target.
Takes no parameters.
Move the cursor to screen coordinates without clicking.
Takes no parameters.
Click and drag from one point to another.
Takes no parameters.
Type text on a Classic Mac target. Characters are typed one by one.
Takes no parameters.
Press a key with optional modifiers. Use for keyboard shortcuts
Takes no parameters.
Select a menu item by menu title and item name
Takes no parameters.
Launch an application on the Classic Mac by path or creator code.
Takes no parameters.
Bring a running application to the front. Requires AgentBridge.
Takes no parameters.
Quit a running application by name. Requires AgentBridge.
Takes no parameters.
Send a generic Apple Event to an application. TARGET is app name or
Takes no parameters.
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Classic Mac costs nothing to install and nothing to call, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| classic-mac-mcp | no tags | |
| classic_mac_list_targets | no tags | |
| classic_mac_ping | no tags | |
| classic_mac_heartbeat | no tags | |
| classic_mac_list_windows | no tags | |
| classic_mac_list_processes | no tags | |
| classic_mac_list_menus | no tags | |
| classic_mac_get_menu_items | no tags | |
| classic_mac_get_front_window | no tags | |
| classic_mac_get_volumes | no tags | |
| classic_mac_list_folder | no tags | |
| classic_mac_get_about | no tags | |
| classic_mac_get_clipboard | no tags | |
| classic_mac_set_clipboard | no tags | |
| classic_mac_click | no tags | |
| classic_mac_mouse_move | no tags | |
| classic_mac_mouse_drag | no tags | |
| classic_mac_type_text | no tags | |
| classic_mac_key_press | no tags | |
| classic_mac_menu_select | no tags | |
| classic_mac_launch_app | no tags | |
| classic_mac_activate_app | no tags | |
| classic_mac_quit_app | no tags | |
| classic_mac_send_appleevent | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 1.0.2 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
No release note was published with this version.
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Writing one takes an account with at least 50 real tool calls against Classic Mac in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.