Connect a Large Language Model to a robot using the Model Context Protocol (MCP) and phosphobot.
git
are installed on your system.phospho
MCP server and registers its tools with Claude. When you open the Claude desktop app, you will see the server and its tools available for use.
http://localhost:80
).
GET /frames
: Fetches the latest camera image.POST /recording/play
: Executes a pre-recorded robot action.PhosphoClient
class manages this communication. If you run phosphobot on a port other than 80, you must update the base URL in the tools/phosphobot.py
file.
“What do you see on my desk?”Claude will use the
get_camera_frame
tool to answer.
“Pick up the banana”Claude will use the
pickup_object
tool to perform the action.
pickup_object
get_camera_frame
phosphobot
?
A: phosphobot
is an open-source platform for robotics that helps you control robots, collect data, and train AI models for robotic tasks.
Q: What is phosphobot mcp
?
A: phosphobot mcp
refers to the integration of the phosphobot platform with the Model Context Protocol. It allows an LLM like Claude to control a robot managed by phosphobot by using standardized tools for actions and camera feeds.
Q: Can I use this with a physical robot?
A: Yes. phosphobot
is designed to control physical robots, allowing you to bridge the gap between AI and hardware.
Q: Can it only use pre-recorded actions?
A: No, while the demo uses pre-recorded actions for simplicity, you can extend the phosphobot MCP server
to include real-time control commands or trigger any AI model trained with phosphobot (eg: ACT, gr00t).