Assess risk metrics including volatility, beta, VaR, and drawdown. Args: symbol: Ticker symbol period: Analysis period (default 1y) position_size: Optional position size in dollars for position-specific metrics
AI agents call risk_assessment 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 analytical/querying tool. It calculates and returns risk statistics based on market data—no side effects, no data modification, no code execution, no financial transactions. The position_size parameter is optional context for calculation, not a financial commitment or transaction. Risk is low because misuse would only return incorrect analysis to the agent, not cause harm to systems or data.
From the tool's definition Tool assesses and retrieves risk metrics (volatility, beta, VaR, drawdown) for a given symbol and period. The description uses only read/analysis verbs: 'Assess' and 'Analyze'.
Documented attack patterns abuse exactly the kind of access risk_assessment 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 risk_assessment:
{
"version": "1",
"default": "deny",
"tools": {
"risk_assessment": {}
}
}risk_assessment 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.
Assess risk metrics including volatility, beta, VaR, and drawdown. Args: symbol: Ticker symbol period: Analysis period (default 1y) position_size: Optional position size in dollars for position-specific metrics. 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 risk_assessment: 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.
risk_assessment 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 risk_assessment 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 risk_assessment. 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.
risk_assessment 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.