AI agents call get_dividend_yield to retrieve information from Tiingo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical dividend yield data without side effects. It is a read-only operation that fetches existing financial information from the Tiingo API. No data is created, modified, deleted, or executed. The low severity reflects minimal risk from misuse—an AI agent could retrieve unnecessary data but cannot cause financial transactions, data corruption, or unintended operations.
From the tool's definition Tool name and description indicate data retrieval: 'Get historical dividend yield data' with no mention of modification, deletion, or execution capabilities. Returns financial metrics for a specified security.
Attacks that exploit this kind of access
Get historical dividend yield data for a stock or ETF. It is categorised as a Read tool in the Tiingo MCP Server, which means it retrieves data without modifying state.
Register the Tiingo MCP server in PolicyLayer and add a rule for get_dividend_yield: 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 Tiingo. Nothing to install.
get_dividend_yield 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_dividend_yield 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_dividend_yield. 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_dividend_yield is provided by the Tiingo MCP server (major7apps/tiingo-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 →