AI agents call get_friend_balances 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 fetches and aggregates existing financial data (balance summaries) for viewing purposes only. It does not create, modify, delete, or execute any financial transactions. It is a read-only query operation with no destructive or transactional impact, making it a low-severity Read category tool.
From the tool's definition Tool retrieves a 'pre-computed net balance summary' with no modification capability. The description emphasizes it is 'much faster than manually summing raw balances', indicating it queries and returns computed data without side effects.
Attacks that exploit this kind of access
Get a pre-computed net balance summary — who owes you, who you owe, and your overall net position across all friends. Much faster than manually summing raw balances. 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_friend_balances: 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_friend_balances 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_friend_balances 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_friend_balances. 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_friend_balances 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 →