READ-ONLY — probe the connected Ledger device over USB HID and report which app is currently open (name + version), plus an actionable hint for the agent to relay. Uses the dashboard-level GET_APP_AND_VERSION APDU so it works whether the user is on the dashboard or inside a chain app — you get 'B...
AI agents call get_ledger_device_info to retrieve information from VaultPilot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_ledger_device_info only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
READ-ONLY — probe the connected Ledger device over USB HID and report which app is currently open (name + version), plus an actionable hint for the agent to relay. Uses the dashboard-level GET_APP_AND_VERSION APDU so it works whether the user is on the dashboard or inside a chain app — you get 'BOLOS' / 'OS' for the dashboard and e.g. 'Solana' 1.10.2 / 'Ethereum' 1.13.0 / 'Tron' 0.2.0 / 'Bitcoin' 2.3.0 when an app is open. deviceConnected: false is returned cleanly (with a hint) when no Ledger is plugged in or the udev rules are missing on Linux; the tool never throws. Call this BEFORE pair_ledger_solana / pair_ledger_tron so you can replace 'open the Solana app and enable blind-signing' with a context-aware instruction like 'I see your Bitcoin app is open — switch to Solana (device → right button → Solana → both buttons)'. One USB round-trip; no chain RPC calls. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
Register the VaultPilot MCP server in PolicyLayer and add a rule for get_ledger_device_info: 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 VaultPilot MCP. Nothing to install.
get_ledger_device_info 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_ledger_device_info 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_ledger_device_info. 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_ledger_device_info is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.