MQTT MCP integration for AI agents.
Connect AI agents to MQTT through 2 structured actions, including publish message and receive messages. Review authentication, inputs, workflows, and safety…
- ACTION CONTRACTS
- 2
- AUTHENTICATION
- Custom credentials
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the MQTT integration exposes
The MQTT Agent App exposes 2 provider-backed actions for developer tools and infrastructure work. Its current contract lets an authorized agent publish one utf-8 or base64-encoded message through a short-lived mqtt-over-websocket connection and wait briefly for new messages on an mqtt topic filter. this is not a persistent subscription and can miss messages between action calls. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses Custom credentials. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected MQTT account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real MQTT capabilities.
Showing 2 of 2 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
publish_messageHIGH IMPACTPublish one UTF-8 or base64-encoded message through a short-lived MQTT-over-WebSocket connection.
INPUTS: topic / payload / payloadEncoding / qos / retain
receive_messagesREVIEWWait briefly for new messages on an MQTT topic filter. This is not a persistent subscription and can miss messages between action calls.
INPUTS: topicFilter / qos / timeoutSeconds / maxMessages / payloadEncoding
INPUT CONTRACTS
Know what the action needs before it runs.
publish_message
topicREQUIRED- Exact MQTT topic to publish to. Topic wildcards are not allowed.
payloadREQUIRED- Message payload encoded according to payloadEncoding.
payloadEncodingOPTIONAL- How to decode payload before publishing it.
qosOPTIONAL- MQTT quality of service level.
retainOPTIONAL- Whether the broker should retain this message for future subscribers.
receive_messages
topicFilterREQUIRED- MQTT topic filter to subscribe to, including + or # wildcards when needed.
qosOPTIONAL- MQTT quality of service level.
timeoutSecondsOPTIONAL- Maximum time to wait for messages before returning.
maxMessagesOPTIONAL- Maximum number of messages to collect before returning.
payloadEncodingOPTIONAL- How received message payloads should be returned.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Publish Message
Publish one UTF-8 or base64-encoded message through a short-lived MQTT-over-WebSocket connection. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
publish_messageControl Publish Message
Publish one UTF-8 or base64-encoded message through a short-lived MQTT-over-WebSocket connection. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
publish_messageVerify with Receive Messages
Wait briefly for new messages on an MQTT topic filter. This is not a persistent subscription and can miss messages between action calls. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
receive_messagesSAFETY BOUNDARY
Operate MQTT with explicit limits
- Authorize MQTT with Custom credentials and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `publish_message` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in MQTT rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the MQTT task completed successfully.
CONNECTION MODEL
Custom credentials
MQTT uses Custom credentials. Connection requirements and availability are determined by the provider and the Working Machines deployment.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 0
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 1
- REVIEW SIGNALS
- 1
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by MQTT.