AI agents call get_session_plan 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 trading analysis and setup recommendations but does not execute trades, modify data, delete information, or move money. It provides read-only intelligence for decision-making. While the output may inform financial decisions, the tool itself only reads/queries data without committing funds or triggering transactions.
From the tool's definition Tool name 'get_session_plan' and description 'Get a full session planner with pattern-driven trade setups for today' indicate retrieval and querying of pre-computed trading information.
Attacks that exploit this kind of access
Get a full session planner with pattern-driven trade setups for today. 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_session_plan: 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_session_plan 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_session_plan 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_session_plan. 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_session_plan 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 →