List the user
AI agents call list_transactions to retrieve information from Luni MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries transaction data from the Luni backend API. While the data is financial in nature, the tool itself only reads and does not execute payments, move money, or commit financial obligations. The severity is low because listing past transactions has minimal blast radius—an agent cannot cause harm by simply viewing transaction history. No side effects or irreversible changes are possible.
From the tool's definition Tool name is 'list_transactions' and server description indicates it 'lets Claude read live financial data from Luni, including personal transactions'. The word 'list' and 'read' confirm retrieval without modification.
Attacks that exploit this kind of access
List the user. It is categorised as a Read tool in the Luni MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Luni MCP Server MCP server in PolicyLayer and add a rule for list_transactions: 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 Luni MCP Server. Nothing to install.
list_transactions 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 list_transactions 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 list_transactions. 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.
list_transactions is provided by the Luni MCP Server MCP server (rorygeddes/luni_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 →