AI agents call mysql_describe 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 retrieves information about database table structures (columns, types, constraints, etc.) without side effects. It is a read operation that enables understanding of data organization but does not create, modify, delete, or execute code. The low severity reflects minimal blast radius—an AI agent misusing this tool can only learn about schema, not compromise data or systems.
From the tool's definition Tool name 'mysql_describe' and description 'Describe table structure' indicate it retrieves metadata about table schemas without modifying or executing arbitrary operations.
Attacks that exploit this kind of access
Describe table structure. 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: 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 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 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. 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 is provided by the Mysql MCP server (myheisenberg/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 →