Kiểm tra phiên bản Katana đã cài đặt
AI agents call katana_check_version to retrieve information from Katana MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves version metadata about an installed application. It performs no modification, deletion, code execution, or financial transaction. It is a simple read operation with no blast radius if misused by an AI agent.
From the tool's definition Tool name 'katana_check_version' and description 'Kiểm tra phiên bản Katana đã cài đặt' (Vietnamese for 'Check installed Katana version') indicate a query operation that retrieves version information without side effects.
Attacks that exploit this kind of access
Kiểm tra phiên bản Katana đã cài đặt. It is categorised as a Read tool in the Katana MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Katana MCP Server MCP server in PolicyLayer and add a rule for katana_check_version: 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 Katana MCP Server. Nothing to install.
katana_check_version 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 katana_check_version 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 katana_check_version. 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.
katana_check_version is provided by the Katana MCP Server MCP server (ngothienan/katana-mcp-server). 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 →