AI agents call get_system_summary to retrieve information from DeviceMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries device metadata with no side effects. It is purely informational, providing system specs, battery status, storage, and memory details. There is no capability to modify, delete, or execute operations. Misuse would only expose read-only system information, posing minimal risk.
From the tool's definition Tool aggregates device information queries (battery level, device info, memory, storage) without modifying state. Description states 'Get a comprehensive summary' indicating retrieval only.
Attacks that exploit this kind of access
Get a comprehensive summary of all device information in one call. It is categorised as a Read tool in the DeviceMCP MCP Server, which means it retrieves data without modifying state.
Register the Device MCP server in PolicyLayer and add a rule for get_system_summary: 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 DeviceMCP. Nothing to install.
get_system_summary 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_system_summary 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_system_summary. 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_system_summary is provided by the Device MCP server (jahidhasanco/devicemcp). 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 →