The Model Context Protocol (MCP) is an open standard for connecting AI models to external tools. It defines a simple contract: a server exposes tools (callable functions), resources (readable data), and prompts (reusable templates).
MCP as the integration layer, not the control layer. The MCP server does not talk directly to hardware. It calls a Hardware API that handles the actual instrument protocol.
One MCP server per instrument class. A liquid handler MCP server exposes tools for aspiration, dispensing, tip handling, and plate management.
The Nature Machine Intelligence X-ray scientist study demonstrates MCP applied to synchrotron beamline motor control — terminal I/O parsing, detector images, and motor scan results exposed as MCP tools.
We are building toward a future where any lab instrument with a digital interface can be wrapped as an MCP server and controlled through natural language. Not to replace scientists — to give them a better interface to their own equipment.
The protocol adapter pattern — instrument protocol to MCP to AI agent — works for scientific instrumentation orchestration.