search_statements
AI agents call search_statements to retrieve information from Investment Statement 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 financial data (investment statements, holdings, transactions, balances) without modifying or deleting data. While the tool description is empty, the server context and naming strongly indicate read-only search functionality.
From the tool's definition Tool name 'search_statements' combined with server's stated purpose of 'Parse and query investment statements' and 'semantic search for dividends, holdings, transactions, and account balances.' The sibling tools (get_account_balance, get_holdings_by_symbol,…
Attacks that exploit this kind of access
search_statements. It is categorised as a Read tool in the Investment Statement MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Investment Statement MCP Server MCP server in PolicyLayer and add a rule for search_statements: 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 Investment Statement MCP Server. Nothing to install.
search_statements 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 search_statements 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 search_statements. 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.
search_statements is provided by the Investment Statement MCP Server MCP server (vinnycarter05/investing-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 →