Skip to main content
Glama
emqx

AIoT MCP Server

Official
by emqx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

AIoT MCP Server

Artificial intelligence Internet of Things (AIoT) is a new paradigm of IoT. It is a combination of artificial intelligence and IoT.

MQTT is particularly well-suited for AIoT networks for several key reasons:

  1. Its publish/subscribe pattern allows for flexible, decoupled communication between AI agents and IoT devices

  2. The lightweight protocol minimizes network overhead, perfect for resource-constrained IoT devices

  3. Topic-based hierarchical structure enables natural organization of device groups and capabilities

  4. Retained messages maintain device state, allowing AI agents to quickly understand system context

  5. Last Will and Testament (LWT) feature helps detect offline devices automatically

This repo demonstrates a MCP server which fetches device context from MQTT broker for MCP client to use.

AIoT Agent Network Protocol

Agents MUST use the following MQTT topic convention:

  • $ai/{DOMAIN}/{GROUP}/d/{DEVICE_ID}: Topic pattern for device registration and discovery

  • $ai/{DOMAIN}/{GROUP}/r/{RULE_ID}: Topic pattern for rule registration and discovery

Agents MUST register clients or rules as retained messages on the corresponding topics. Agents MUST use readable text to describe the device or rule. Agents MAY use natural language to describe the device or rule.

This is ALL.

Related MCP server: mcp2mqtt

Prompt

The assistant's prompt is defined in assistant-prompt.md. This file contains the instructions and capabilities given to the AI assistant for interacting with IoT devices through MQTT.

Tools

Discover

Discovers devices and rules in a group using MQTT topic filter. When querying the status of a group, provide the device GROUP as the argument.

Example request:

{
  "group": "room1"
}

Example response:

[
  {
    "topic": "$ai/room1/123",
    "message": "I am a temperature sensor..., I publish ... to topic room1/123/status"
  },
  {
    "topic": "$ai/room1/456",
    "message": "I am an air conditioner..., I subscribe to topic room1/456/command, expect payload to be on/off"
  }
]

Publish

Publishes a message to a device using MQTT topic and payload.

Example request:

{
  "topic": "room1/456/command",
  "payload": "on",
  "qos": 0,
  "retain": false
}

Query

Queries a specific topic for its current state.

Example request:

{
  "topic": "room1/123/status"
}

Configuration

The server can be configured using environment variables:

  • MQTT_BROKER_URL: MQTT broker URL (default: mqtt://127.0.0.1:1883)

  • MQTT_USERNAME: MQTT username (optional)

  • MQTT_PASSWORD: MQTT password (optional)

Running The Server

Claude Desktop configuration:

{
  "mcpServers": {
    "aiot": {
      "command": "npx",
      "args": [ "tsx", "/path/to/this/repo/src/index.ts" ]
    }
  }
}

Available Tools

3 tools
discoverA

Discover devices and rules in a group using MQTT topic filter. When asked status of a group, provide the device GROUP as the argument. If no group is provided, discover all devices and rules in the domain.

ParametersJSON Schema
NameRequiredDescriptionDefault
groupNo

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the burden. It discloses MQTT topic filter usage and default scope behavior (all vs. group), but does not explicitly state read-only nature, return format, or permission requirements. 'Discover' implies non-mutating, but specifics are limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with the core action and scope. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter discovery tool with no output schema, the description covers the primary scenario, optional behavior, and domain scope. It lacks return-shape details, but the tool is simple enough that this is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description adds meaningful semantics for the 'group' parameter: it is a device GROUP, used when status of a group is requested, and optional with a clear default. It does not provide format examples, but compensates well for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'discover[s] devices and rules' scoped by group or entire domain, using an MQTT topic filter. This specific verb+resource+scope distinguishes it from siblings publish and query.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: use a device GROUP when asking status of a group, and omit group to discover everything in the domain. It does not explicitly name alternate tools or when-not-to-use, but the guidance is practical and distinct.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

publishA

Publish a message to a device using MQTT topic and payload. When asked to control a device, you should use this tool with the topic argument discovered from the "discover" tool. For example, a device might describe itself subscribing to a topic livingroom/456/command, then this is the topic to be used to control the device.

ParametersJSON Schema
NameRequiredDescriptionDefault
qosNo
topicYes
retainNo
payloadYes

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It explains the core behavior (publish MQTT topic+payload) and the device-control context. However, it does not disclose potential side effects, return values, error conditions, or whether the publish is confirmed, which are relevant for an operation with no annotations or output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences that front-load the core purpose and then add a helpful usage example. Every sentence contributes meaning; there is no redundancy or unnecessary details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple publish tool with 4 parameters, no output schema, and no annotations, the description provides a clear use case and example but omits details about optional parameters, expected return behavior, and error handling. It is adequate for basic invocation but not fully complete for risk-free autonomous use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, yet the description only explains 'topic' (with a usage example) and 'payload' by name. The optional parameters 'qos' and 'retain' are not mentioned at all, and no additional meaning is added for payload. Given the low schema coverage, this is insufficient for full parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool publishes a message to a device using MQTT topic and payload. It explicitly distinguishes itself from siblings by linking usage to controlling a device and referencing the 'discover' tool for topic discovery. The example reinforces the purpose and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: use when asked to control a device, with the topic discovered from the 'discover' tool. Includes a concrete example. However, it does not mention when not to use it (e.g., for reading data, which may be covered by 'query'), leaving a slight gap in alternative selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

queryA

When asked status of a device, provide the device TOPIC as the argument. The topic can be found in previous messages from the "discover" tool. For example, a device might describe itself publishing its status to a topic livingroom/456/status, then this is the topic to be used to query the status of the device.

ParametersJSON Schema
NameRequiredDescriptionDefault
topicYes

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains how to provide the argument but does not disclose what the tool returns, whether it is a read-only operation, error behavior, or side effects. It implies a query/read action but stops short of describing the tool's actual behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the key trigger condition. The example adds useful concrete detail without excessive verbosity. It could be slightly tighter, but each sentence contributes to understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool, the description covers the basic invocation and param provenance. However, since there is no output schema and no annotations, the description should ideally mention what the tool returns or any relevant behavioral outcomes. It is minimally viable but leaves some gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines 'topic' as a required string with no description, so the description must compensate. It does so effectively by explaining how to find the topic (from previous 'discover' messages) and providing a concrete example of a topic string, giving meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to query the status of a device by providing a topic. It uses a specific verb and resource ('query status' by topic), and the example makes the intent concrete. It does not explicitly differentiate from sibling tools 'discover' and 'publish', though the focus on querying status is distinct enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool ('When asked status of a device') and gives a concrete prerequisite: the topic must come from previous messages from the 'discover' tool. It does not explicitly state when not to use it or name alternatives, but the contextual guidance is clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observeddiscover
    • First observedpublish
    • First observedquery
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a distinct purpose: discover finds devices/rules, publish sends commands, query retrieves status. No overlap in functionality; the descriptions clearly differentiate them.

Naming Consistency5/5

All tool names are single verbs in lowercase, following a consistent imperative style (discover, publish, query). No mixing of conventions or styles.

Tool Count5/5

Three tools is well-scoped for an MQTT-based AIoT server, covering discovery, control, and status query. Each tool earns its place without unnecessary bloat or missing core operations.

Completeness4/5

The core lifecycle of discovering, controlling, and querying devices is covered. A minor gap is the lack of explicit rule management (create/update/delete), but rules are discovered via the discover tool, and the primary IoT interactions are complete.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp2mqtt

    swesmith-repos
    A
    license
    B
    quality
    Not graded
    maintenance
    An MCP server that bridges the physical world and AI models by enabling natural language control of IoT hardware via the MQTT protocol. It supports real-time device monitoring, command publishing, and response handling for seamless integration between AI clients and physical devices.
    3
    MIT

  • node-red-mcp

    ziv-daniel
    F
    license
    Not graded
    quality
    A
    maintenance
    A Model Context Protocol server for Node-RED integration, enabling AI agents to manage flows, install modules, and monitor Node-RED instances via natural language.
    5
    -

  • MQTT MCP Server

    ezhuk
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables LLM agents to securely monitor and control MQTT devices for building automation, industrial control, and smart home systems through a standardized MCP interface.
    22
    MIT