get_expense_summary
Total expenses for a year with by-category and by-month breakdowns. Answers "what did I spend on software this year?" or "where is my money going?"
This record as markdown: /tools/com-getsavitools-savi-tools/get-expense-summary.md
What get_expense_summary does on Savi Tools
AI agents call get_expense_summary to retrieve information from Savi Tools without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
year | integer | — | Calendar year. Defaults to the current year. |
category | string | — | Optional category name to filter to (e.g. "Software & Subscriptions"). |
Parameters from the server's own tool schema.
Why get_expense_summary is rated Low
This tool only retrieves and summarizes existing expense data. It does not create, modify, or delete financial records, execute transactions, or trigger external operations. The blast radius of misuse is minimal — an AI agent could only extract summary information that the user's business has already recorded. No financial movements, data destruction, or code execution occurs.
From the tool's definition Tool retrieves aggregate expense data with 'by-category and by-month breakdowns' and answers queries like 'what did I spend' and 'where is my money going' — all read operations that query existing financial summaries without modification, deletion, or…
Attacks that exploit this kind of access
The rule that runs get_expense_summary safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Savi Tools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_expense_summary, this is the rule to start with:
get_expense_summary is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Savi Tools, apply this rule, and every get_expense_summary call is checked against it from then on.
Questions about get_expense_summary
Total expenses for a year with by-category and by-month breakdowns. Answers "what did I spend on software this year?" or "where is my money going?". It is categorised as a Read tool in the Savi Tools MCP Server, which means it retrieves data without modifying state.
get_expense_summary accepts 2 parameters: year, category. The full parameter table on this page comes from the server's own tool schema.
Register the Savi Tools MCP server in PolicyLayer and add a rule for get_expense_summary: 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 Savi Tools. Nothing to install.
get_expense_summary 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_summary 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_summary. 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_summary is provided by the Savi Tools MCP server (https://getsavitools.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Savi Tools, and thousands of servers like it.
This server
Across the catalogue