查看指定資料表的欄位結構
AI agents call describe-table to retrieve information from MSSQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves schema metadata about table columns, which is a read-only operation. No data is modified, deleted, or executed. It only returns structural information about a table. The MSSQL server itself is advertised as supporting 'secure SELECT queries', and describe-table is analogous to DESCRIBE/sp_help queries which are non-destructive metadata reads.
From the tool's definition Tool name is 'describe-table' and description states it views field structure of specified tables ('查看指定資料表的欄位結構' = 'view the field structure of a specified table'). This is a metadata query operation with no side effects.
Attacks that exploit this kind of access
查看指定資料表的欄位結構. It is categorised as a Read tool in the MSSQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MSSQL MCP Server 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 MSSQL MCP Server. 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 MSSQL MCP Server MCP server (nakiriyuuzu/mssql-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 →