mqtt_query · MCP MQTT Server MCP: Risk & Policy

WHAT IT DOES

What mqtt_query does on MCP MQTT Server

AI agents invoke mqtt_query to trigger actions in MCP MQTT Server. 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.

WHY IT NEEDS A POLICY

Why mqtt_query needs a policy

mqtt_query goes beyond passive reading: it sends an outbound request message to a topic and awaits a reply, constituting an external operation whose effects depend on the message payload and target topic. In IoT contexts, such requests can trigger actuators, device state changes, or commands on physical hardware, making this an Execute-category tool.

From the tool's definition "Send a request and wait for response on specified topics" — this tool actively sends a request (publish) and waits for a response, triggering a two-way interaction with external IoT devices or systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mqtt_query Rate-limited

mqtt_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mqtt_query": {
      "limits": [
        {
          "counter": "mqtt_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP MQTT Server, so you can run agents against it safely.

FAQ

Questions about mqtt_query

What does the mqtt_query tool do? +

Send a request and wait for response on specified topics. It is categorised as a Execute tool in the MCP MQTT Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mqtt_query? +

Register the MCP MQTT Server MCP server in PolicyLayer and add a rule for mqtt_query: 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 MQTT Server. Nothing to install.

What risk level is mqtt_query? +

mqtt_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mqtt_query? +

Yes. Add a rate_limit block to the mqtt_query 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.

How do I block mqtt_query completely? +

Set action: deny in the PolicyLayer policy for mqtt_query. 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.

What MCP server provides mqtt_query? +

mqtt_query is provided by the MCP MQTT Server MCP server (tspspi/mcpmqtt). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.