Detect institutional whale option activity for a given underlying. Uses a two-step approach: 1. Crude scan via Yahoo Finance — finds contracts with anomalous daily investment. 2. Precise drill-down via Massive API — per-second bars for each candidate. Requires MASSIVE_API_KEY environment variable...
AI agents call whale_hunting to retrieve information from Trading Skills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure market data analysis and reconnaissance tool. It queries Yahoo Finance and the Massive API to identify and examine options activity patterns, but does not execute trades, modify positions, or commit financial transactions. The institutional whale activity detection is analytical in nature — it reads market data to inform decision-making but imposes no side effects on accounts, positions, or orders.
From the tool's definition Tool performs detection and analysis of institutional option activity through data scanning and drilling down into market data. Core functions are 'Detect' and 'drill-down via Massive API' — retrieves per-second bars and finds anomalous contracts.
Documented attack patterns abuse exactly the kind of access whale_hunting gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trading Skills, and nothing reaches the server without passing your rules. This is the rule we recommend for whale_hunting:
{
"version": "1",
"default": "deny",
"tools": {
"whale_hunting": {}
}
}whale_hunting is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Detect institutional whale option activity for a given underlying. Uses a two-step approach: 1. Crude scan via Yahoo Finance — finds contracts with anomalous daily investment. 2. Precise drill-down via Massive API — per-second bars for each candidate. Requires MASSIVE_API_KEY environment variable for per-second data. Falls back to Yahoo-only daily data if unavailable. Args: symbol: Underlying ticker (e.g. AAPL, NVDA, SPY) max_months: Max months until expiration to consider (default 2) trading_date: Date to analyze YYYY-MM-DD (default: latest trading day) sigma_z: Modified Z-Score threshold for outlier detection (default 3.5) summary: If True, include per-ticker aggregate summary in result. It is categorised as a Read tool in the Trading Skills MCP Server, which means it retrieves data without modifying state.
Register the Trading Skills MCP server in PolicyLayer and add a rule for whale_hunting: 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 Trading Skills. Nothing to install.
whale_hunting 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 whale_hunting 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 whale_hunting. 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.
whale_hunting is provided by the Trading Skills MCP server (staskh/trading_skills). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 35 Trading Skills tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
35 Trading Skills tools catalogued and risk-classified — across an index of 42,500+ MCP servers.