指定年の下落日ワーストランキング
AI agents call get_worst_days to retrieve information from Market Index MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical market performance rankings (worst trading days in a given year) without modifying, executing operations, or affecting financial transactions. It is a pure data query operation with no side effects, fitting the Read category. Severity is low because misuse would only expose historical financial data analysis, not enable destructive or financial actions.
From the tool's definition Tool name 'get_worst_days' and description indicating retrieval of worst-performing days for a specified year. The server provides 'natural language access to over 100 years of historical market index data' for querying and analysis.
Attacks that exploit this kind of access
指定年の下落日ワーストランキング. It is categorised as a Read tool in the Market Index MCP MCP Server, which means it retrieves data without modifying state.
Register the Market Index MCP server in PolicyLayer and add a rule for get_worst_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 Market Index MCP. Nothing to install.
get_worst_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_worst_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_worst_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_worst_days is provided by the Market Index MCP server (tamappe/market-index-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 →