AI agents call get_index_stocks to retrieve information from Gurufocus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of stocks in an index—a read-only operation with no side effects. No data is created, modified, deleted, or executed. The 'get_' prefix and alignment with sibling query tools confirm it queries GuruFocus financial data. Low severity because retrieving stock lists poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_index_stocks' follows retrieval pattern (get_*); sibling tools include get_api_usage, get_economic_indicator, get_etf_list, get_exchange_stocks, all clearly Read operations that query financial data without modification.
Attacks that exploit this kind of access
get_index_stocks. It is categorised as a Read tool in the Gurufocus MCP Server, which means it retrieves data without modifying state.
Register the Gurufocus MCP server in PolicyLayer and add a rule for get_index_stocks: 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 Gurufocus. Nothing to install.
get_index_stocks 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_index_stocks 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_index_stocks. 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_index_stocks is provided by the Gurufocus MCP server (u-daveblack/gurufocus-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 →