Search through all stored financial data using semantic search.
AI agents call query_financial_history to retrieve information from My Finance MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
query_financial_history retrieves and searches existing financial transaction data without modifying, deleting, or executing operations. Misuse would expose sensitive financial information but cannot move money, delete records, or trigger external financial operations. The risk is information disclosure rather than financial commitment or data loss.
From the tool's definition Tool description states 'Search through all stored financial data using semantic search' — a read-only query operation.
Attacks that exploit this kind of access
Search through all stored financial data using semantic search. It is categorised as a Read tool in the My Finance MCP Server MCP Server, which means it retrieves data without modifying state.
Register the My Finance MCP Server MCP server in PolicyLayer and add a rule for query_financial_history: 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 My Finance MCP Server. Nothing to install.
query_financial_history 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 query_financial_history 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 query_financial_history. 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.
query_financial_history is provided by the My Finance MCP Server MCP server (xinrong-meng/my-finance-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 →