AI agents call get_similar_days 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 is a data query tool that searches and retrieves historical records matching specified criteria. It performs analysis on existing data without side effects, making it a Read operation. The low severity reflects that misuse would only return informational data, posing minimal risk to systems or financial positions. The high confidence reflects clear Read semantics in both name and description.
From the tool's definition Tool name 'get_similar_days' and description 'Find historical days with conditions similar to today' indicate retrieval of historical data for comparison purposes. No modification, deletion, code execution, or financial transactions occur.
Attacks that exploit this kind of access
Find historical days with conditions similar to 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_similar_days: 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_similar_days 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_similar_days 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_similar_days. 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_similar_days 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 →