yahoo_search
AI agents call yahoo_search to retrieve information from YFinance MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context indicate this is a search/retrieval function that queries Yahoo Finance for market data without modifying anything. Even though the tool description is empty, the naming convention and sibling tools strongly suggest read-only data retrieval. No financial transactions occur—only information access.
From the tool's definition Tool name is 'yahoo_search' and sibling tools (yahoo_chart, yahoo_quote, yahoo_quote_summary, yahoo_stock_history) are all retrieval operations. Server description emphasizes 'retrieval of real-time quotes, historical data' and 'market searches'.
Attacks that exploit this kind of access
yahoo_search. It is categorised as a Read tool in the YFinance MCP Server MCP Server, which means it retrieves data without modifying state.
Register the YFinance MCP Server MCP server in PolicyLayer and add a rule for yahoo_search: 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 YFinance MCP Server. Nothing to install.
yahoo_search 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 yahoo_search 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 yahoo_search. 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.
yahoo_search is provided by the YFinance MCP Server MCP server (szemeng76/yfinance-mcp-server). 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 →