Return column names and types for a table.
AI agents call describe_table to retrieve information from Mcp Sqlserver 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 table structure (column names and types) without any side effects or data modification. It is a non-destructive query operation that returns schema information only, fitting squarely within the Read category with minimal risk.
From the tool's definition Tool description states 'Return column names and types for a table' with no modification capability. Server description emphasizes 'read-only queries' and lists this as a schema discovery operation alongside 'listing tables' and 'describing database schemas'.
Attacks that exploit this kind of access
Return column names and types for a table. It is categorised as a Read tool in the Mcp Sqlserver MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sqlserver MCP server in PolicyLayer and add a rule for describe_table: 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 Sqlserver. Nothing to install.
describe_table 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 describe_table 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 describe_table. 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.
describe_table is provided by the Mcp Sqlserver MCP server (mlsloynaz/mcp-sql-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 →