AI agents call bluetooth_scan to retrieve information from Sysprobe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a discovery scan of nearby Bluetooth devices, which is a non-destructive, non-mutating read operation. It retrieves information about available devices without creating, modifying, or deleting any data. The server's description notes a 'safety model that requires explicit flags for mutating actions,' and this tool lacks any indication of such flags, further confirming its read-only nature.
From the tool's definition Scan for nearby Bluetooth devices for a few seconds — this is a passive read operation that queries available Bluetooth devices without modifying any state or triggering actions.
Attacks that exploit this kind of access
Scan for nearby Bluetooth devices for a few seconds. It is categorised as a Read tool in the Sysprobe MCP Server, which means it retrieves data without modifying state.
Register the Sysprobe MCP server in PolicyLayer and add a rule for bluetooth_scan: 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 Sysprobe. Nothing to install.
bluetooth_scan 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 bluetooth_scan 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 bluetooth_scan. 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.
bluetooth_scan is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →