AI agents call mysql_tables 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 and enumerates table metadata from a database. It has no side effects, does not modify data, and does not execute arbitrary code. It is a straightforward read operation analogous to schema inspection. Severity is low because misuse would only expose database structure information, not compromise data integrity or enable financial harm.
From the tool's definition Tool name is 'mysql_tables' and description states 'List all tables in a database' — a pure query operation with no modification, deletion, or code execution.
Attacks that exploit this kind of access
List all tables in a database. 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_tables: 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_tables 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_tables 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_tables. 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_tables 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 →