mcpField
R
Rocuronium

Rocuronium

Local
kagerou.glassProductivity4Updated today
RepositoryVisit website

About Rocuronium

Rocuronium is a macOS automation system that gives an AI agent a separate login session and cursor. It combines accessibility data and local vision for UI control, and reports evidence showing whether interactions took effect.

Key features

  1. 01Dedicated macOS session and cursor
  2. 02Accessibility trees and on-device OCR
  3. 03Click, type, scroll, and window controls
  4. 04Evidence for interaction outcomes
  5. 05Sequential plans with failure policies
  6. 06CLI and MCP session controls

Use cases

  1. 01Automate app interfaces without using the human cursor
  2. 02Verify whether a UI action changed the screen
  3. 03Find controls in apps with sparse accessibility data
  4. 04Pause or stop an agent's macOS session

MCP support

Provides MCP tools to inspect or stop a session. Creating a session requires human approval.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
mcpbrocuronium-1.6.1.mcpb1.6.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Rocuronium

Rocuronium gives an AI agent a separate macOS login session with its own desktop and cursor. Local vision models help find UI elements when accessibility data is missing, and each interaction returns evidence of what actually changed: confirmed, noEffect, or unverifiable.

Download Rocuronium for Mac

Rocuronium reports an unchanged click, requests cursor approval, then confirms the interaction

Highlights

  • Work in a separate login session while the agent uses its own desktop and cursor.
  • Detect failed interactions even when macOS reports that the API call succeeded.
  • Find controls with local vision models when an app exposes little accessibility information.
Full feature list
  • Observation: accessibility trees, element search, on-device OCR, window screenshots, and structural or pixel diffs.
  • Interactions: click, type, keys, shortcuts, menus, scrolling, app launch, and window controls.
  • Evidence: confirmed, noEffect, or unverifiable, with read-back, focus, window, selection, or pixel changes.
  • Isolation: a dedicated agent session, virtual displays, and window parking.
  • Plans: sequential actions with postconditions and abort, continue, pause-for-human, or fallback policies.
  • Human control: visible activity, approval before taking the human cursor, and emergency stop ⌃⌥⇧⎋. Resume requires the app’s popover.
  • Automation: CLI and MCP tools. Session creation requires human approval; MCP can inspect or stop a session.

Notes

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.