AI agents call get_regime 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 a volatility regime score (0-100) from the server's analytics. It is a pure read operation—no data is created, modified, deleted, or financial action taken. Even in the context of an AI trading agent, misuse would only affect decision-making based on stale or incorrect data, not cause direct harm.
From the tool's definition Tool name 'get_regime' and description 'Get the CRC (Curistat Regime Composite) reading, a 0-100 score' indicate a retrieval operation that queries existing regime data without modifying, executing operations, or committing financial transactions.
Attacks that exploit this kind of access
Get the CRC (Curistat Regime Composite) reading, a 0-100 score. 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_regime: 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_regime 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_regime 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_regime. 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_regime 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 →