# Connecting a Raspberry Pi to LLM agents through MCP

DevFeed: [Connecting a Raspberry Pi to LLM agents through MCP](<https://devfeed.tech/articles/connecting-a-raspberry-pi-to-llm-agents-through-mcp-137901.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/17/connecting-a-raspberry-pi-to-llm-agents-through-mcp/>)

Author: Anne Barela

Published: 2026-11-17T16:33:13Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [air-quality](<https://devfeed.tech/tags/air-quality.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [ens160](<https://devfeed.tech/tags/ens160.md>), [esp32](<https://devfeed.tech/tags/esp32.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [motion](<https://devfeed.tech/tags/motion.md>), [mpu6050](<https://devfeed.tech/tags/mpu6050.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [single-board-computers](<https://devfeed.tech/tags/single-board-computers.md>), [ws2812b](<https://devfeed.tech/tags/ws2812b.md>)

## AI overview

The PHOS project connects an LLM agent to room sensors through a Raspberry Pi MCP server. An ESP32 reads environmental sensors, including ENS160 and MPU6050, drives a WS2812B LED ring, and sends newline-delimited JSON over USB to the Pi. The Pi exposes semantic tools, such as describing the room, so the agent can request useful information without addressing individual sensors. MCP resources can also provide a camera JPEG from the existing vision pipeline. Sensor readings track reliability and warm-up status, helping prevent the agent from reporting air-quality data before the sensor is ready.

## Source excerpt

Francesco Azzola published a project on Hackster.io that connects an LLM agent to real sensors using a Raspberry Pi and the Model Context Protocol, or MCP, a standard way for AI agents to call outside tools. An ESP32 handles the hardware. It reads environmental sensors, an ENS160 air-quality sensor and an MPU6050 motion sensor, and [...]