AI agents call get_forecast_week to retrieve information from Curistat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves forward-looking volatility forecasts, which is a read-only operation. It does not create, modify, delete, or execute any trading actions. While it provides intelligence that could inform trading decisions, the tool itself merely queries and returns predictive data with no side effects. No financial transactions are initiated by this tool.
From the tool's definition Tool name is 'get_forecast_week' and description states 'Get 5-day forward volatility forecast.' This is purely a data retrieval operation that queries forecasting models without modifying any data or executing commands.
Attacks that exploit this kind of access
Get 5-day forward volatility forecast. It is categorised as a Read tool in the Curistat MCP Server, which means it retrieves data without modifying state.
Register the Curistat MCP server in PolicyLayer and add a rule for get_forecast_week: 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 Curistat. Nothing to install.
get_forecast_week 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_forecast_week 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_forecast_week. 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_forecast_week is provided by the Curistat MCP server (moxiespirit/curistat-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 →