Get complete inventory attributes for a specific device
AI agents call get_device_inventory to retrieve information from Mender MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves device inventory data without modifying, executing, or deleting anything. It is a straightforward read operation that queries existing device information. The blast radius of misuse is limited to potential information disclosure, which is inherently low-severity compared to write, execute, or destructive operations.
From the tool's definition Tool name is 'get_device_inventory' and description states 'Get complete inventory attributes for a specific device.' This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get complete inventory attributes for a specific device. It is categorised as a Read tool in the Mender MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mender MCP Server MCP server in PolicyLayer and add a rule for get_device_inventory: 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 Mender MCP Server. Nothing to install.
get_device_inventory is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_device_inventory 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 get_device_inventory. 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.
get_device_inventory is provided by the Mender MCP Server MCP server (pasinskim/mender-mcp). 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 →