按列名/类型/备注进行检索（支持 SQL LIKE 语法）
AI agents call searchColumns to retrieve information from SQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs read-only queries on database schema information (column names, types, remarks). It retrieves data without side effects, matching the 'Read' category definition. Within a read-only SQL server context with SQL injection protection, the blast radius of misuse is minimal (information disclosure only).
From the tool's definition Tool name 'searchColumns' and description indicate searching/retrieving column metadata by name, type, or remarks using SQL LIKE syntax. No modification, deletion, or execution of queries is performed—only metadata exploration and retrieval.
Attacks that exploit this kind of access
按列名/类型/备注进行检索（支持 SQL LIKE 语法）. It is categorised as a Read tool in the SQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SQL MCP Server MCP server in PolicyLayer and add a rule for searchColumns: 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 SQL MCP Server. Nothing to install.
searchColumns 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 searchColumns 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 searchColumns. 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.
searchColumns is provided by the SQL MCP Server MCP server (polarisxb/sql-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 →