Complete risk tearsheet: Sharpe, Sortino, VaR, Kelly, drawdown, Hurst, CAGR. Replaces 7 individual calls. Use when you need a complete risk tearsheet for a return series. Instead of calling 7 individual risk/stats endpoints, this returns Sharpe, Sortino, Calmar, VaR, CVaR, Kelly, max drawdown, H...
Part of the Quantoracle MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call risk_full-analysis to retrieve information from Quantoracle without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though risk_full-analysis only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
risk_full-analysis:
rules:
- action: allowSee the full Quantoracle policy for all 74 tools.
Agents calling read-class tools like risk_full-analysis have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Complete risk tearsheet: Sharpe, Sortino, VaR, Kelly, drawdown, Hurst, CAGR. Replaces 7 individual calls. Use when you need a complete risk tearsheet for a return series. Instead of calling 7 individual risk/stats endpoints, this returns Sharpe, Sortino, Calmar, VaR, CVaR, Kelly, max drawdown, Hurst exponent, CAGR, and win rate in one call. Provide daily returns. Returns: comprehensive risk profile with portfolio values. PAID ONLY — no free tier.. It is categorised as a Read tool in the Quantoracle MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for risk_full-analysis. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Quantoracle MCP server.
risk_full-analysis 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_full-analysis rule in your Intercept 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 Intercept policy for risk_full-analysis. 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_full-analysis is provided by the Quantoracle MCP server (QuantOracle/quantoracle). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept