SHOW CREATE TABLE
AI agents call show_create_table to retrieve information from MySQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
SHOW CREATE TABLE is a read-only operation that queries and returns the CREATE TABLE statement for a table, enabling schema inspection. It does not create, modify, delete, or execute arbitrary code. This aligns with the Read category (retrieves or queries data; no side effects).
From the tool's definition Tool is 'show_create_table' which executes SHOW CREATE TABLE - a standard MySQL DDL introspection query that retrieves table schema definition. It has no side effects and only returns metadata about table structure.
Attacks that exploit this kind of access
SHOW CREATE TABLE. It is categorised as a Read tool in the MySQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MySQL MCP Server MCP server in PolicyLayer and add a rule for show_create_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 MCP Server. Nothing to install.
show_create_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 show_create_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 show_create_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.
show_create_table is provided by the MySQL MCP Server MCP server (yclenove/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 →