建立 MQTT IoT 裝置連線
AI agents use mqtt_device_create to create or update resources in MCP API Bridge Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP API Bridge Server environment.
This tool creates or initializes a new MQTT device connection, which is a reversible write operation. It modifies the state of the IoT system by adding a new device entity, but the action can be undone by deleting the device. It does not execute arbitrary code, destroy data irreversibly, or move funds, making Write the appropriate category.
From the tool's definition Tool name 'mqtt_device_create' and description '建立 MQTT IoT 裝置連線' (Create MQTT IoT device connection) indicates creation of a new device connection/resource in the MQTT IoT system.
Attacks that exploit this kind of access
建立 MQTT IoT 裝置連線. It is categorised as a Write tool in the MCP API Bridge Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP API Bridge Server MCP server in PolicyLayer and add a rule for mqtt_device_create: 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 API Bridge Server. Nothing to install.
mqtt_device_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mqtt_device_create 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_device_create. 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_device_create is provided by the MCP API Bridge Server MCP server (marty5499/mcp-api-bridge). 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 →