テーブルのカラム情報を取得します（ラベル付き）。
AI agents call get_columns to retrieve information from AS400 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 column metadata (names, labels, data types) from AS400/IBM i tables. It performs a read-only query operation with no capability to modify, execute, or delete data. The server explicitly provides 'read-only access' and this tool falls squarely within that constraint. Low severity because metadata queries pose minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_columns' and server description emphasizing 'read-only access to metadata'; Japanese description translates to 'Retrieve column information for tables (with labels)', which is a metadata query operation with no side effects.
Attacks that exploit this kind of access
テーブルのカラム情報を取得します（ラベル付き）。. It is categorised as a Read tool in the AS400 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AS400 MCP Server MCP server in PolicyLayer and add a rule for get_columns: 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 AS400 MCP Server. Nothing to install.
get_columns 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_columns 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_columns. 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_columns is provided by the AS400 MCP Server MCP server (kozokaai/as400-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 →