Publish a message to an MQTT topic
AI agents invoke mqtt_publish to trigger actions in Mcp Coordinator. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Publishing to MQTT is an external side-effecting operation: it dispatches a message to a broker which may trigger subscribers, automation systems, or other agents. This goes beyond a simple write (local data creation/modification) into executing an external communication/event trigger.
From the tool's definition 'Publish a message to an MQTT topic' — triggers an external operation by sending a message to an MQTT broker, whose effects depend on the topic and payload arguments
Attacks that exploit this kind of access
Publish a message to an MQTT topic. It is categorised as a Execute tool in the Mcp Coordinator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Coordinator MCP server in PolicyLayer and add a rule for mqtt_publish: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Coordinator. Nothing to install.
mqtt_publish is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mqtt_publish rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mqtt_publish. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mqtt_publish is provided by the Mcp Coordinator MCP server (swoofer/mcp-coordinator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →