AI agents call mysql_describe_table to retrieve information from Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about table structure (columns, indexes) with no side effects. It is purely informational, fitting the Read category. Severity is low because metadata disclosure has limited blast radius compared to data exfiltration or modification. Confidence is high due to the explicit read-only nature and the server's stated safety design.
From the tool's definition Tool description states it "Return[s] column metadata and optional indexes for a table." Server description emphasizes "read-only MySQL query execution" with "SQL safety validation." The tool retrieves schema information without modifying data.
Attacks that exploit this kind of access
Return column metadata and optional indexes for a table. It is categorised as a Read tool in the Mysql MCP Server, which means it retrieves data without modifying state.
Register the Mysql MCP server in PolicyLayer and add a rule for mysql_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 Mysql. Nothing to install.
mysql_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 mysql_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 mysql_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.
mysql_describe_table is provided by the Mysql MCP server (xujcbiz/mysql-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 →