Build a step-by-step guide for the user to exit demo mode and switch to operational (real signing) mode. The MCP server CANNOT actually unset VAULTPILOT_DEMO or invoke the setup wizard — both require user action outside the MCP. This tool produces a tailored decision tree the agent walks the user...
AI agents invoke exit_demo_mode to trigger actions in VaultPilot MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
chains | array | — | Chains the user intends to use. Drives which RPC / API keys to recommend. Defaults to ['ethereum'] when omitted. |
hasLedger | boolean | — | Whether the user confirmed they have a Ledger device. Pass `false` to get a deferral message recommending they stay in demo until they have hardware. Omit if un |
acquireKeys | boolean | — | Whether the user wants help acquiring API keys. Affects recommendation tone — true expands signup links, false keeps the response short. |
hasRunSetup | boolean | — | Whether the user has previously run `vaultpilot-mcp-setup`. When true, the response skips the setup-wizard walkthrough. |
Parameters from the server's own tool schema.
exit_demo_mode triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Build a step-by-step guide for the user to exit demo mode and switch to operational (real signing) mode. The MCP server CANNOT actually unset VAULTPILOT_DEMO or invoke the setup wizard — both require user action outside the MCP. This tool produces a tailored decision tree the agent walks the user through. Stateless / read-only — calling it does NOT change demo state. AGENT BEHAVIOR — call this tool ONLY after explicitly confirming with the user that they want to leave demo mode (e.g., 'I'm ready to set this up for real', 'I have my Ledger now', 'exit demo'). DO NOT call it as a probe — the response is verbose and presumes intent. Before calling, ASK the user: (1) do you have a Ledger device? (2) have you already run vaultpilot-mcp-setup? (3) which chains do you intend to use? Pass the answers as args so the response is tailored. If hasLedger=false, the response recommends DEFERRING the exit (without a Ledger, operational mode gives no functionality demo doesn't already have). Surface that verbatim. Outside demo mode, the tool returns a no-op response indicating there's nothing to exit. It is categorised as a Execute tool in the VaultPilot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
exit_demo_mode accepts 4 parameters: chains, hasLedger, acquireKeys, hasRunSetup. The full parameter table on this page comes from the server's own tool schema.
Register the VaultPilot MCP server in PolicyLayer and add a rule for exit_demo_mode: 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.
exit_demo_mode is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the exit_demo_mode 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 exit_demo_mode. 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.
exit_demo_mode 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.