IvoryOS MCP
@ivoryzh
IvoryOS is a Python-based unified robot control web interface, developed for user-friendly workflow design and control for Self-Driving Labs (SDLs). It works by introspecting the Python script, dynamically searching for available module and their method. The methods are available
Overview
What is IvoryOS MCP?
IvoryOS MCP serves as a robot control interface using IvoryOS and the Model Context Protocol (MCP) to design, manage workflows, and interact with the current hardware/software execution layer.
How to use IvoryOS MCP?
Install uv, clone the repository, and install dependencies with uv pip install -r uv.lock. Configure the IvoryOS URL and login credentials in a .env file or directly in ivoryos_mcp/server.py. Then install the server in Claude Desktop using mcp install ivoryos_mcp/server.py.
Key features of IvoryOS MCP
- Get IvoryOS platform info and signature (
platform-info) - List, load, and submit workflow scripts from the database
- List and load workflow execution data (CSV and logs)
- Call platform functions directly with
execute-task - Run workflow scripts repeatedly or with dynamic parameters
- Pause, resume, abort, or safely stop workflow execution
Use cases of IvoryOS MCP
- Obtain real-time platform information and execution status
- Design and manage robot workflow scripts programmatically
- Run repeated or parameterised robot workflows from an AI assistant
- Pause or abort running workflows safely without hardware risk
FAQ from IvoryOS MCP
What are the prerequisites to install IvoryOS MCP?
You need uv installed, Python, and the cloned repository. Dependencies are handled via uv pip install -r uv.lock.
How do I configure the IvoryOS server connection?
Set IVORYOS_URL, IVORYOS_USERNAME, and IVORYOS_PASSWORD in a .env file, or modify the corresponding variables directly in ivoryos_mcp/server.py.
How do I install the server in Claude Desktop?
Run mcp install ivoryos_mcp/server.py after configuring the environment. Claude Desktop will then be able to use the MCP tools.
What is the difference between ℹ️ and 🤖 tools?
Tools marked ℹ️ (General, Workflow Design, Workflow Data) are read-only or safe and can be allowed always. Tools marked 🤖 (Direct Control, Workflow Run, Workflow Control) trigger actual hardware/software actions and should be allowed once per invocation.
