AI agents call get_expense to retrieve information from Splitwise without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves expense data without modifying, deleting, or creating records. It is a query operation that returns information about a specific expense. The blast radius of misuse is minimal—an AI agent could retrieve expense records it shouldn't see (information disclosure), but cannot modify financial state or trigger transactions. This is a standard Read operation.
From the tool's definition Tool description: 'Get a single Splitwise expense by ID with full split details.' The verb 'Get' and the read-only operation of retrieving an expense record by ID indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get a single Splitwise expense by ID with full split details. It is categorised as a Read tool in the Splitwise MCP Server, which means it retrieves data without modifying state.
Register the Splitwise MCP server in PolicyLayer and add a rule for get_expense: 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 Splitwise. Nothing to install.
get_expense 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_expense 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_expense. 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_expense is provided by the Splitwise MCP server (saharshpatel24/splitwise-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 →