AI agents call get_direction 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.
This tool retrieves and aggregates pre-computed trading signals to provide directional bias information. It performs only data retrieval and analysis—no side effects, code execution, financial transactions, or irreversible changes. It is informational only, providing market intelligence without triggering trades or external operations.
From the tool's definition Tool name 'get_direction' and description 'Get directional bias from a 17-component signal aggregate' indicate retrieval of analytical data with no modification, deletion, execution, or financial action.
Attacks that exploit this kind of access
Get directional bias from a 17-component signal aggregate. 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_direction: 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_direction 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_direction 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_direction. 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_direction 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 →