search_columns
AI agents call search_columns to retrieve information from Oracle MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description lowering confidence slightly, the tool name 'search_columns' strongly suggests a search/discovery operation on database schema metadata. Sibling tools like 'get_table_constraints', 'get_table_indexes', and 'get_object_source' are all clearly Read operations for schema inspection. This tool fits that same pattern. No evidence of write, execute, or destructive capability.
From the tool's definition Tool name 'search_columns' with no description provided. Based on naming convention and context within an Oracle schema introspection server, this appears to be a query tool for discovering column metadata.
Attacks that exploit this kind of access
search_columns. It is categorised as a Read tool in the Oracle MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Oracle MCP Server MCP server in PolicyLayer and add a rule for search_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 Oracle MCP Server. Nothing to install.
search_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 search_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 search_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.
search_columns is provided by the Oracle MCP Server MCP server (zhengwanbo/oracle-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 →