Search for tables or columns containing a specific keyword
AI agents call search_tables to retrieve information from MCP SQL Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about database structure (tables and columns matching a keyword) without executing queries, modifying data, or triggering side effects. It is a lookup/discovery function analogous to a list or search operation, making it a Read category risk with low severity.
From the tool's definition Tool name is 'search_tables' with description 'Search for tables or columns containing a specific keyword' — this is a pure query/search operation with no modification or execution capabilities.
Attacks that exploit this kind of access
Search for tables or columns containing a specific keyword. It is categorised as a Read tool in the MCP SQL Agent MCP Server, which means it retrieves data without modifying state.
Register the MCP SQL Agent MCP server in PolicyLayer and add a rule for search_tables: 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 MCP SQL Agent. Nothing to install.
search_tables 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_tables 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_tables. 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_tables is provided by the MCP SQL Agent MCP server (sharansahu/mcp-sql). 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 →