AI agents call krx_schema to retrieve information from Krx Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about API schemas—it does not modify, execute operations, delete data, or move money. It is a simple introspection tool that helps users understand available data fields before making actual queries. The read-only nature and lack of any operational side effects classify it as a Read category risk with low severity.
From the tool's definition Tool description states it 'Returns field names and descriptions for each endpoint' and is used to 'discover available fields before querying data.' This is purely informational retrieval with no side effects.
Attacks that exploit this kind of access
Query response field schemas for KRX API endpoints. Returns field names and descriptions for each endpoint. Use this to discover available fields before querying data. It is categorised as a Read tool in the Krx Cli MCP Server, which means it retrieves data without modifying state.
Register the Krx Cli MCP server in PolicyLayer and add a rule for krx_schema: 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 Krx Cli. Nothing to install.
krx_schema 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 krx_schema 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 krx_schema. 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.
krx_schema is provided by the Krx Cli MCP server (kyo504/krx-cli). 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 →