AI agents call describe_table 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 queries and returns schema information (column names, types, constraints, etc.) without creating, modifying, deleting, or executing arbitrary operations. This is a read-only inspection operation with minimal blast radius if misused by an agent. The presence of execute_query as a sibling tool confirms this one is restricted to schema inspection.
From the tool's definition Tool name is 'describe_table' and description states 'Show the schema for a specific table' — this retrieves metadata about table structure with no modification or deletion capability.
Attacks that exploit this kind of access
Show the schema for a specific table. 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 describe_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 Mariadb. Nothing to install.
describe_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 describe_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 describe_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.
describe_table 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 →