Austin Robotics & AI Meetup/Talk: Robot MCP

Model Context Protocol (MCP) has emerged as the standard for connecting AI systems with external tools, creating new opportunities to bridge models such as Claude, ChatGPT, and Gemini with existing robot ecosystems. These generalist AI models are rapidly improving in their ability to perceive, reason, and plan. However, most robots today are built on stable software stacks and middleware, making end-to-end AI integration costly and impractical.

In this talk, we introduce Model Context Protocol in accessible terms and then walk through Robot MCP, an open-source server that applies this standard to robotics. Demonstrated on ROS (the most prevalent robotics middleware) Robot MCP enables new classes of tasks that neither AI models nor traditional deterministic robotics could accomplish independently.

We will showcase example interactions and highlight emergent behaviors observed when AI models were given real-time access to robot functions — from unexpected problem-solving strategies to notable limitations.

Attendees will leave with:
An understanding of Model Context Protocol and its relevance to robotics.
A practical method for linking AI models to existing robots without rebuilding from scratch.
First-hand insights into emergent behaviors that highlight both the opportunities and challenges of AI-driven robotics.
------
Speaker Bio:
Rohit John Varghese is the Director of Systems Engineering and Product at Contoro Robotics, a company developing AI-driven logistics robots for shipping container unloading. Previously, Rohit was Vice President of Research & New Product at Harmonic Bionics, where he led development of the Harmony SHR medical exoskeleton and from research concept to FDA registration and eventual acquisition. His work spans exoskeletons, human–robot interaction, teleoperation, and AI-enabled robotic systems, and he is always curious to explore any domain to its first principles.
Rohit has served as faculty at The University of Texas at Austin, where he taught graduate courses in robotics, and as an industry mentor for National Science Foundation (NSF) programs. He also leads the development of the Robot MCP server, an open-source project that connects AI models with robotic systems using Model Context Protocol.

‍