AI agents call list_databases to retrieve information from Mariadb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about available databases without creating, modifying, deleting, or executing any operations. It has minimal blast radius—enumeration of database names poses low risk. While it reveals database structure information that could inform further attacks, the tool itself is purely informational. Confidence is high due to clear naming and description indicating read-only access.
From the tool's definition Tool name 'list_databases' and description 'List all accessible databases' indicate a query-only operation with no side effects. This is a retrieval operation similar to 'list_tables' (a sibling tool also in the Read category).
Attacks that exploit this kind of access
List all accessible databases on the MariaDB server. It is categorised as a Read tool in the Mariadb MCP Server, which means it retrieves data without modifying state.
Register the Mariadb MCP server in PolicyLayer and add a rule for 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 Mariadb. Nothing to install.
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 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 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.
list_databases is provided by the Mariadb MCP server (mariadb-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 →