AI agents call get_wallet to retrieve information from Luxxon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns financial account information (balance and blockchain sync state) without creating transactions, modifying balances, or executing commands. It is a read-only operation on existing data. While it touches financial data, it does not move money, commit financial obligations, or incur charges—making it Read rather than Financial.
From the tool's definition Tool retrieves 'Workspace pool balance + last on-chain sync block' for informational purposes; no state modification occurs. The description emphasizes checking balance 'to decide whether to top up', indicating a pure query operation.
Attacks that exploit this kind of access
Workspace pool balance + last on-chain sync block. Use to decide whether to top up before a session. It is categorised as a Read tool in the Luxxon MCP Server, which means it retrieves data without modifying state.
Register the Luxxon MCP server in PolicyLayer and add a rule for get_wallet: 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 Luxxon. Nothing to install.
get_wallet 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_wallet 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_wallet. 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_wallet is provided by the Luxxon MCP server (luxxon-dev/luxxon-sdk). 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 →