AI agents call mysql_list_databases 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 database metadata with no side effects. It is purely informational, consistent with the Read category. Severity is low because database enumeration poses minimal risk—it reveals schema structure but cannot access, modify, or delete data without additional tools.
From the tool's definition Tool name 'mysql_list_databases' and server description stating 'read-only MySQL query execution' and 'database/table browsing'. The description explicitly indicates this lists databases with no modification capability.
Attacks that exploit this kind of access
List databases visible to the configured read-only MySQL user. 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_list_databases: 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_list_databases 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_list_databases 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_list_databases. 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_list_databases 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 →