Get latest news for a stock symbol
AI agents call get_news to retrieve information from Yahoo Finance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available news information for a given stock symbol. It has no side effects, does not modify any data, does not execute code or commands, and does not involve financial transactions. It is a straightforward read operation that queries existing news data from Yahoo Finance.
From the tool's definition Tool name is 'get_news' and description states 'Get latest news for a stock symbol' — purely retrieves and queries public financial news data with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get latest news for a stock symbol. It is categorised as a Read tool in the Yahoo Finance MCP Server, which means it retrieves data without modifying state.
Register the Yahoo Finance MCP server in PolicyLayer and add a rule for get_news: 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 Yahoo Finance. Nothing to install.
get_news 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_news 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_news. 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_news is provided by the Yahoo Finance MCP server (nrempel/yahoo-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 →