Beyond MQTT. EMQX is pioneering the unified nervous system for AI and IoT, from autonomous vehicles, smart manufacturing to robotics.
Standardized, bidirectional communication for edge AI agents. Built-in service registry and discovery via the MQTT broker.
Broker-neutral profile for agent discovery, request/reply messaging, and event delivery across distributed AI agent systems.
Reliable connectivity over unstable networks with 0-RTT handshake.
Real-time messaging bus for robotics, industrial automation, and autonomous driving.
Native support for durable data stream storage and replay within the MQTT broker.
Pack multiple messages into a single MQTT 5.0 PUBLISH to reduce overhead and boost throughput.
Explore our latest blog posts, tutorials, and news at the intersection of MQTT, IoT, and AI.
This article connects the Microduck robot in the MuJoCo simulator to Device Agent, using a DeviceSpec to describe its commands, properties and events. Users can then make the robot walk, turn and kick a ball with text or voice commands, and automate those actions with workflows and scheduled tasks.
Learn how to control the Microduck robot with MQTT and MuJoCo, and explore Device Agent for LLM-powered edge-cloud robotics and natural-language control.
This article explores how to build an intelligent Home Energy Management System (HEMS) using the EMQ Device Agent and IoT Platform.
Deepen your understanding with our collection of white papers, solution briefs, and expert guides on MQTT and AI.
Find answers to common questions about MQTT for AI.
MQTT for AI represents the next generation of MQTT protocol enhancements specifically designed for intelligent IoT applications. It includes four key innovations: MQTT over QUIC for reliable connectivity in mobile scenarios, MCP over MQTT for AI agent communication, MQTT/RT for real-time industrial automation, and MQTT streams for durable data storage and replay. These enhancements enable EMQX to serve as a unified nervous system for intelligent IoT, connecting everything from autonomous vehicles to factory robotics with edge AI capabilities.
MCP over MQTT uses MQTT as a transport for the Model Context Protocol (MCP), making MCP a better fit for IoT, edge computing, and cloud-to-edge deployments where MQTT is already the messaging backbone. It adds built-in service registry and discovery (clients can find available MCP servers via the broker) and supports scalable deployments by adding more server instances. It's not meant to replace existing MCP transports (stdio / HTTP SSE), but to provide an alternative for remote MCP servers and edge AI agent scenarios.
They target scale and efficiency. MQTT Streams/Queues introduce native durable storage, retention, replay/offset-based consumption, and buffering semantics in the broker—useful for data pipelines, offline processing, and edge-to-cloud backpressure. Batch publishing allows multiple logical messages to be packed into a single MQTT 5.0 PUBLISH to reduce header/topic overhead and improve throughput. Subscription filters add a second layer of filtering at subscribe time so subscribers receive only the subset of messages they actually need, reducing bandwidth and downstream processing.